WO2013014877A1 - Reliability calculation device, method for using translation reliability calculation, and program for translation engine - Google Patents
Reliability calculation device, method for using translation reliability calculation, and program for translation engine Download PDFInfo
- Publication number
- WO2013014877A1 WO2013014877A1 PCT/JP2012/004541 JP2012004541W WO2013014877A1 WO 2013014877 A1 WO2013014877 A1 WO 2013014877A1 JP 2012004541 W JP2012004541 W JP 2012004541W WO 2013014877 A1 WO2013014877 A1 WO 2013014877A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- translation
- reliability
- result
- language
- reverse
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/40—Processing or translation of natural language
- G06F40/51—Translation evaluation
Definitions
- the present invention relates to a reliability calculation device for determining the reliability of machine translation and speech translation, a reliability calculation usage method, and a program for a translation engine.
- Patent Document 1 discloses a method of using reliability (RSCM) based on the sum of ranks in a machine translation output candidate selection apparatus. This method is based on the top hypothesis of each N-best based on the ranking of hypotheses that are translation candidates among the top N translation candidates (N-best) output by statistical machine translation (Statistic Machine Translation: SMT). The posterior probability of the word is calculated and the reliability is obtained.
- RSCM reliability
- SMT statistical Machine Translation
- Patent Document 2 when machine translation from a reference text in a first language into a text in a second language is performed, the translated text in the second language is converted into a folded translation text in the first language.
- a data conversion appropriate evaluation method is described in which the similarity between the reference text before translation and the data in the first language after reverse conversion is converted into an appropriate conversion value.
- Patent Document 3 discloses the N best hypothesis output from a speech recognition module in a machine translation system that performs speech recognition and machine translation into a second language for input speech in a first language. And re-scoring each of N ⁇ K translation candidates based on the K translation candidates for each of the N best hypotheses output from the statistical machine translation module and the information associated therewith. A configuration including a rescoring module that outputs a translation that achieves the highest score as the best translation is described.
- Patent Document 1 the method described in Patent Document 1 is based on the premise that statistical machine translation is used as a translation process. For this reason, it is not applicable when using grammatical rule type translation that performs translation processing on a grammar base (rule base). This is because the concept of likelihood is not clear in grammatical rule translation. Currently, it is generally considered that grammatical rule-based translation can achieve more accurate translation than statistical machine translation.
- Patent Document 1 gives reliability only to the processing result of machine translation. Therefore, when there is an unclear part in the input-side sentence in machine translation, it is not possible to prompt the user who has the input-side language to appropriately input again.
- machine translation after performing speech recognition on a sentence that is input in speech, if there is a possibility that it will eventually be translated correctly if part of the original sentence is changed, It is difficult for the user on the input side to determine whether or not to re-input the original text only with the reliability of the translation processing result.
- Patent Document 2 If the method described in Patent Document 2 is used, the reliability of machine translation can be obtained without assuming statistical machine translation as machine translation. However, since the method described in Patent Document 2 gives reliability only to the processing result of machine translation, as in Patent Document 1, it is appropriately re-input to a user having an input language. There is a problem that cannot be urged.
- the method described in Patent Document 3 combines N ⁇ K translation candidate candidates by combining feature amounts (for example, likelihood information reflecting each accuracy) obtained from the speech recognition module and the machine translation module. Since a score is assigned to each of these, it may be possible to obtain a translation result with higher reliability in consideration of not only the result of translation processing but also the result of speech recognition processing.
- the method described in Patent Document 3 assumes statistical machine translation as machine translation. Further, it is only assumed that the re-scored score is used to select the best translation from a plurality of translation candidates. For this reason, it is difficult to understand where the problem is in the evaluation that is calculated by unifying by modeling, and it is not possible to prompt the user to appropriately input again based on the reliability.
- An object of the present invention is to provide a reliability calculation device, a translation reliability calculation usage method, and a translation engine program.
- the reliability is the first for the sentence or sentence data (for example, speech data) in the input first language.
- This refers to the reliability of the final processing result of machine translation performed through language recognition processing. That is, it means the reliability considering not only the processing result of the machine translation process but also the processing result of the preceding recognition process.
- the reliability calculation apparatus includes a translation unit that performs translation processing on an input sentence into a second language that is different from the first language that is the language of the input sentence, and translation processing that is performed by the translation unit
- a reverse translation means for performing a reverse translation process to the first language which is the language of the input sentence, and a reverse translation result obtained as a result of the reverse translation process by the input sentence and the reverse translation means.
- a translation reliability calculation means for calculating a translation reliability based on the distance between the input sentence, the translation result, and the reverse translation result, at least one of the input sentence, the translation result, and the reverse translation result.
- a reliability presenting means for presenting to the user together with the degree of reliability and the reliability presenting means first outputs at least the input sentence or the reverse translation result together with the translation reliability when the translation reliability is below a predetermined threshold. Enter the language of Characterized in that it presents on the part of the user.
- the translation reliability calculation and utilization method performs a translation process on an input sentence into a second language that is different from the first language that is the language of the input sentence, and results of the translation process
- the translation result is reverse translated into the first language, which is the language of the input sentence, and the translation reliability is determined based on the distance between the input sentence and the reverse translation result obtained as a result of the reverse translation process.
- the translation reliability is equal to or lower than a predetermined threshold
- at least the input sentence or the reverse translation result is presented to the user who has input the first language together with the translation reliability.
- the translation engine program includes a computer, a translation process for converting an input sentence described in a first language into a second language that is a language different from the first language, and a result of the translation process.
- Translation that calculates translation reliability based on the distance between the reverse translation process that converts the obtained translation result into the first language that is the language of the input sentence, and the reverse translation result that is obtained as a result of the reverse translation process
- a reliability calculation process and a reliability presentation process for presenting at least one of the input sentence, the translation result, and the reverse translation result together with the reliability corresponding to the input sentence, the translation result, or the reverse translation result to the user.
- the reliability presentation process if the translation reliability is equal to or lower than a predetermined threshold, at least the input sentence or the reverse translation result is presented to the user who has input the first language together with the translation reliability. And wherein the door.
- the reliability of the translation result can be appropriately obtained, and when the reliability is low, the input user is appropriately re-input Can be encouraged.
- FIG. FIG. 1 is a block diagram showing a configuration example of a reliability calculation apparatus according to the first embodiment of the present invention.
- the reliability calculation apparatus 10 shown in FIG. 1 inputs text or a character string, performs machine translation, calculates the reliability, and outputs it.
- the reliability calculation device 10 includes a machine translation unit 13, a reverse translation unit 14, and a translation reliability calculation unit 15.
- the reliability calculation apparatus 10 includes an input unit 11 and an output unit 12 directly or indirectly. Note that “indirectly” means, for example, that other devices connected via a network may be provided.
- the reliability calculation device 10 may be, for example, a general-purpose computer system that includes a CPU, RAM, ROM, and non-volatile storage device (not shown). That is, in the reliability calculation device 10, an information processing device such as a CPU reads an OS and a reliability calculation program stored in a RAM, a ROM, or a non-volatile storage device, and executes predetermined processing including reliability calculation processing. It may be configured to. Thereby, the reliability of a translation result can be output. In addition, the reliability calculation apparatus 10 does not need to be one computer system, and may be configured by a plurality of computers.
- the input unit 11 is a keyboard or the like for inputting a sentence described in a first language before translation, that is, an original sentence, to the reliability calculation apparatus 10. Note that the input unit 11 may input instruction information indicating in which language the original sentence is translated.
- the output unit 12 is a display or the like that displays the reliability output from the reliability calculation device 10 to the user.
- the machine translation unit 13 translates the input original sentence into a translated second language sentence, that is, a translated sentence.
- the technique used as the translation technique may be statistical machine translation, grammatical rule translation, or example-based translation. Since the translation technique itself is well known as a known technique, a detailed description thereof is omitted here.
- the reverse translation unit 14 receives the translation translated by the machine translation unit 13 and translates the input translation into the original first language.
- the translation method here may be a method different from the translation method in the machine translation unit 13, but it is generally easier to use the same method.
- the translation reliability calculation unit 15 receives the original text described in the first language before translation and the reverse translation result translated into the first language again by the reverse translation unit 14, and reverses the input original text. Find the distance from the translation result and use it as the reliability.
- the reliability calculated by the translation reliability calculation unit 15 (specifically, the reliability with respect to the translation processing result of the machine translation unit 13) is referred to as translation reliability.
- the translation reliability calculated here is directly used as the reliability for the translation result.
- the translation reliability calculation unit 15 may obtain an evaluation value based on a predetermined scale representing the distance between the original text and the reverse translation result, that is, the closeness between the two sentences, for example, using a BLEU score using the shared N-gram number. Good.
- the BLEU score is a scale used in the evaluation of statistical machine translation, and the word chain (N-gram) that is shared by both of how much the sentence of a certain translation result can reproduce the correct sentence. This is obtained using the number of and is output in the range of 0 to 1.
- An example of a BLEU score calculation formula is shown below as Formula (1).
- BP represents a penalty longitudinal
- N represents represents the maximum length of the N-gram
- w n denotes a coupling weight (which may be 1 / N)
- P n is modified N-gram accuracy Represents.
- the modified N-gram accuracy is obtained by dividing the maximum value of the shared N-gram number by the total N-gram number.
- the BLEU score has a problem that it becomes low accuracy when the sentence is short, but accuracy can be improved by combining with other measures such as reliability of speech recognition as described later.
- the example which uses a BLEU score as distance was shown here, the calculation method of distance is not restricted to this method.
- the distance between the original text and the reverse translation result in units of words or word strings.
- the obtained word unit reliability may be normalized for the whole sentence, or the whole sentence reliability may be regarded as the simultaneous probability of the reliability of each word unit. Good.
- Equation (2) is obtained by normalizing the word posterior probabilities for the entire sentence when the translation reliability of each word w i constituting the sentence ⁇ w n l ⁇ is CM MT (w i ), and the translation reliability CM. It is a calculation example in the case of extending MT in sentence units.
- equation (3) is a calculation example in the case where the reliability of each word is regarded as a probability event, and the translation reliability CM MT is expanded in sentence units with the reliability of the entire sentence as the joint probability.
- the assignment of reliability has the same meaning whether it is given to the reverse translation result or the original text before translation. That is, the low confidence interval can be presented not only for the translation result but also for the input original text or reverse translation result.
- FIG. 2 is a flowchart illustrating an example of a processing flow of the reliability calculation process in the reliability calculation apparatus 10 of the present embodiment.
- the reliability calculation device 10 inputs a text that is an original sentence to be translated (step S ⁇ b> 100).
- the input of the sentence described in the first language, that is, the original sentence is received via the input unit 11, and the received original sentence is output to the machine translation unit 13 and the translation reliability calculation unit 15.
- the machine translation unit 13 translates the input original text (step S101).
- the machine translation unit 13 performs a translation process on the input original sentence from the first language that is the original language to the second language that is the other language specified, and reversely translates the translation result To the unit 14.
- the reverse translation unit 14 performs reverse translation on the translation that is the translation result of the machine translation unit 13 (step S102).
- the reverse translation unit 14 executes a translation process from the second language, which is the translated language, to the first language, which is the original language, again on the translation that is the translation result input from the machine translation unit 13.
- the reverse translation result, which is the translation result is output to the translation reliability calculation unit 15.
- the translation reliability calculation unit 15 calculates the reliability (step S103).
- the translation reliability calculation unit 15 includes the original text described in the first language before translation input via the input unit 11 and the reverse translation result translated into the first language again by the reverse translation unit 14. Is input, and the distance between the two is calculated as the reliability.
- the distance as the translation reliability is preferably obtained using a shared N-gram, but is not limited thereto.
- the reliability calculation device 10 outputs the result (step S104).
- the reliability calculation device 10 outputs the translation reliability obtained by the translation reliability calculation unit 15 via the output unit 12 such as a display and displays it to the user. At this time, the reliability calculation device 10 may output the reverse translation result together with the translation reliability.
- the distance between the original text and the reverse translation result is calculated when calculating the distance between the original text and the reverse translation result.
- the original text and the reverse translation result may be expanded synonymously.
- a synonym expansion unit 161 and a synonym dictionary 162 may be further provided as in the reliability calculation device 10b illustrated in FIG.
- FIG. 3 is a block diagram illustrating another configuration example of the reliability calculation apparatus according to the present embodiment.
- the synonym dictionary 162 stores words or word strings that have the same meaning but different pronunciations and notations.
- the synonym expansion unit 161 expands each word or word string of the original text or the reverse translation result into a plurality of different expressions using the synonym dictionary 162.
- the translation reliability calculation unit 15 calculates distances for a plurality of candidates that have been synonymously expanded by the synonym expansion unit 161, and finally calculates the distance from the closest candidate. You may select as translation reliability. By adopting such a configuration, for example, even if a word has the same meaning but has the same meaning but different notation as a result of reverse translation, it can be determined that the distance is close if the meaning is the same. Therefore, it is possible to more appropriately calculate the reliability by preventing the distance from being unduly increased.
- FIG. 4 is a block diagram illustrating another configuration example of the reliability calculation apparatus according to the present embodiment.
- the distance between the original sentence and the reverse translation result obtained by reversely translating the translated sentence that is the translation processing result into the original language is calculated as the translation reliability.
- the reliability can be appropriately calculated even by using a translation method other than statistical machine translation such as type translation.
- a translation method other than statistical machine translation such as type translation.
- the machine translation apparatus 100 illustrated in FIG. 5 includes an input unit 11, a reliability calculation unit 10, a result determination unit 110, and an output unit 12.
- the machine translation apparatus 100 is realized by a general-purpose computer system including a CPU, a RAM, a ROM, and a nonvolatile storage device, for example. That is, the CPU may be configured to read a machine translation program in which the operations of the reliability calculation unit 10 and the result determination unit 110 are described in a program language, and execute machine translation processing according to the read program.
- the machine translation apparatus 100 does not have to be a single computer system, and may be configured by a plurality of computer systems. In such a configuration, the machine translation apparatus 100 operates as, for example, one translation engine, and provides a highly accurate translation result as a result by rejecting a low-reliability result.
- the input unit 11 receives the text of the first language input to the apparatus and outputs it to the reliability calculation unit 10.
- the input unit 11 may be a keyboard as a text input device, for example.
- the reliability calculation unit 10 receives a text input from the input unit 11 and performs a translation process and a reliability calculation process.
- the reliability calculation unit 10 corresponds to the reliability calculation device 10 of FIG. Therefore, only the operation different from that in FIG. 1 will be described below, and the description of the same operation as the configuration in FIG. 1 will be omitted.
- the reliability calculation unit 10 in this example may correspond to the reliability calculation device 10b in FIG. 3 or the reliability calculation device 10c in FIG.
- the machine translation unit 13 not only outputs to the reverse translation unit 14 a sentence that has been translated from the first language into the second language, that is, the translation, and also outputs it to the result determination unit 110.
- the translation reliability calculation unit 15 outputs the calculated reliability to the result determination unit 110.
- the result determination unit 110 determines whether or not the translation of the translation result input from the machine translation unit 13 should be output according to the reliability input from the translation reliability calculation unit 15. For example, if the input reliability is greater than or equal to a predetermined threshold value, the translation result is output, and if not, it is determined that the reliability is low and the result is rejected without outputting the translation result.
- the output unit 12 outputs a translation that is a translation result obtained from the result determination unit 110.
- the translated text that is, the text written in the second language may be displayed on the screen, or may be read out as a voice using a speaker incorporating a voice synthesizer for outputting the text.
- the output part 12 does not need to output anything when the result determination part 110 rejects a translation result, and outputs a reverse translation result and reliability with the message which shows that it rejected. Also good.
- the reliability calculation unit 10 includes the machine translation unit 13, but the configuration uses an existing machine translation unit (such as a search engine) included in the machine translation apparatus 100. It is also possible to do. In such a case, the reverse translation unit 14 may perform reverse translation using a translation engine provided in the machine translation apparatus 100.
- FIG. 6 is a flowchart showing an example of the processing flow of translation processing in the first embodiment of the present invention.
- the machine translation apparatus 100 inputs text in a first language (step S200). Specifically, the machine translation apparatus 100 accepts text in the first language input via the input unit 11 and outputs the text to the reliability calculation unit 10.
- the machine translation device 100 translates the input text (step S201). Specifically, the machine translation device 100 performs translation processing into the second language by the machine translation unit 13 on the text of the first language input from the user via the input unit 11. The translation result is output to the reverse translation unit 14 and the result determination unit 110.
- the machine translation apparatus 100 performs reverse translation (step S202). Specifically, the machine translation apparatus 100 performs reverse translation processing on the translation result obtained by the machine translation unit 13 to the first language again by the reverse translation unit 14.
- the machine translation device 100 calculates the reliability (step S203). Specifically, in the translation reliability calculation unit 15 of the machine translation apparatus 100, the original text described in the first language before translation input via the input unit 11 and the first in the reverse translation unit 14 again. The reverse translation result translated into the language is input, and the distance between the two is calculated as the reliability.
- FIG. 7 is an explanatory diagram showing an example of calculation of reliability in this embodiment.
- the translation result in Japanese as the second language is “What.
- the reverse translation result completely reproduces the input sentence, and the reliability of the input sentence and the reverse translation result is 1.0 when the BLEU score is calculated in 1-gram.
- the synonym expansion unit 161 may expand each word or word string of the original text or the reverse translation result into a plurality of candidates using the synonym dictionary 162.
- the translation reliability calculation unit 15 calculates the distance for each combination of a plurality of synonym expanded candidates, and selects the closest one as the final translation reliability. Also good. For example, on the source side of Fig. 7 (b), “chairs” is converted to “sofas", “stools", etc., or “do you have” is converted to "are there", etc. May be.
- “lecture” may be converted into “class” or the like and expanded into a plurality of candidates.
- the distances may be calculated for all combinations of the plurality of candidates developed in this manner, and the closest one may be selected as the reliability.
- the expansion to a plurality of candidates may be any one.
- the machine translation apparatus 100 performs a result determination (step S204). Specifically, the machine translation apparatus 100 determines whether the result determination unit 110 should output the translation of the translation result notified from the machine translation unit 13 according to the reliability notified from the translation reliability calculation unit 15. Judgment. For example, in the case of FIG. 7A, since the reliability is as high as 1.0, it is determined that acceptance, that is, output is possible. Further, in the case of FIG. 7B, since the reliability is as low as 0.0, rejection, that is, output is impossible.
- the machine translation apparatus 100 outputs the result (step S205). Specifically, the machine translation apparatus 100 outputs the translation result obtained as a result of the determination by the result determination unit 110 via the output unit 12 and displays the result on a display, for example.
- the translation result may be output and the reliability may be displayed at the same time.
- the reverse translation result may be displayed together with the reliability to prompt the user to input again.
- the reliability may be presented as shown in FIGS. 7C and 7D, for example.
- FIG. 7C for the input sentence “what would you like to drink” in English as the first language, the translation result in Japanese as the second language is Suppose you want to (nani wo nomitaidesuka) ”and the reverse translation result is“ What ⁇ wouldnyou like to drink?”. At this time, since the reverse translation result completely reproduces the input sentence, the reliability is 1.0 for all words.
- the translation result in Japanese, which is the second language for the input sentence “which will you take”, which is the first language, is “Who are you?
- the reliability is set to 1.0 for 1-gram where the surface layers match, and 0.0 for non-matching
- the reliability value is not limited to this.
- 0.8 may be used if only the surface layer is matched
- 0.9 may be used if the parts of speech are also matched, and only the difference in utilization (you and your in the example of FIG. 7D). If so, a score of 0.3 is also possible.
- FIG. 8 is a block diagram illustrating a configuration example of the reliability calculation apparatus according to the second embodiment of this invention.
- the reliability calculation device 10d illustrated in FIG. 8 receives the word or word string of the speech recognition result and the reliability thereof, and outputs a reliability obtained by integrating the reliability of the speech recognition result and the reliability of the translation result.
- the reliability calculation device 10d may include a speech recognition result input unit 210 and an output unit 12 directly or indirectly.
- the machine translation unit 13, the reverse translation unit 14, and the translation reliability calculation unit 15 are the same as those in the first embodiment shown in FIG. Below, only a different part from 1st Embodiment is demonstrated.
- the speech recognition result input unit 210 inputs a speech recognition result for a sentence or sentence to be translated input by speech and its reliability.
- the machine translation unit 13 and the translation reliability calculation unit 15 receive the speech recognition result from the speech recognition result input unit 210 as the original text.
- the reliability integration unit 21 inputs the speech recognition reliability, which is the reliability of the speech recognition result, from the speech recognition result input unit 210, and further inputs the translation reliability from the translation reliability calculation unit 15. Integrate reliability and translation reliability.
- the reliability integration unit 21 may integrate the speech recognition reliability and the translation reliability by linear interpolation, for example, to obtain an integrated reliability.
- the integrated reliability is CM
- the speech recognition reliability is CM ASR
- the translation reliability is CM MT
- the integrated reliability CM is expressed by the following equation (4) using the linear interpolation coefficient ⁇ .
- CM (1 ⁇ ) ⁇ CM ASR + ⁇ ⁇ CM MT Formula (4)
- CM ASR speech recognition reliability
- word posteriori probability Word Posteriori Probability
- the method of providing the voice recognition reliability is not limited to this. Since the method for calculating the word posterior probability is well known as a known technique, a detailed description thereof is omitted here.
- the translation reliability CM MT is given in sentence units
- the speech recognition reliability CM ASR is often given in word units like word posterior probabilities.
- the speech recognition reliability CM ASR may be extended in sentence units.
- the obtained word posterior probabilities may be normalized for the entire sentence, or the posterior probabilities for the entire sentence may be regarded as the joint probabilities for each word posterior probability. .
- Equation (5) is obtained by normalizing the word posterior probabilities for the entire sentence, where P (w i
- the following formula (6) is a calculation example in the case where the posterior probability of the whole sentence is regarded as the simultaneous probability of each word posterior probability and the speech recognition reliability CM ASR is expanded in sentence units.
- the shared N-gram and the speech recognition N-gram language model or the voice recognition reliability CM ASR are combined in units of words or word strings. This is possible. For example, for a word that is not a shared N-gram, that is, a word that has not been reproduced by reverse translation, a certain penalty value is added to the speech recognition reliability CM ASR to obtain an integrated reliability CM in units of words. Normalize the whole sentence. Thus, by obtaining the integrated reliability in units of words, it becomes possible to present a low reliability section within a sentence.
- the output unit 12 is a display or the like that displays the reliability (here, integrated reliability) output from the reliability calculation device 10d to the user.
- the output unit 12 may display the reliability obtained for each sentence or each word along with the translation result.
- the reliability of the recognition result may be used when assuming other modules such as translation reliability and speech recognition in the input unit. Good. These may be used in combination as the integrated reliability.
- the speech recognition result is input as the original text, but the configuration placed in the previous stage is not limited to speech recognition.
- a similar configuration is possible by inputting a character input result (or character recognition result) using an OCR (Optical Character Reader) or a touch panel and its reliability.
- OCR Optical Character Reader
- the synonym expansion unit 161 and the synonym dictionary 162 are provided and synonym expansion is performed, so that more appropriate reliability calculation can be performed.
- FIG. 10 is a block diagram illustrating another configuration example of the reliability calculation apparatus according to the present embodiment.
- the reliability presented by the reliability presentation unit 17 does not need to be in units of sentences (or the entire utterance), and may be presented in units of words, for example.
- FIG. 9 is a flowchart illustrating an example of a processing flow of reliability calculation processing in the reliability calculation device 10d of the present embodiment.
- the reliability calculation device 10d inputs a speech recognition result as an original sentence to be translated and its reliability (step S300).
- the input of the speech recognition result is accepted as a sentence written in the first language, that is, the original text via the speech recognition result input section 210, and the received original text is sent to the machine translation section 13 and the translation reliability calculation section 15.
- Output At the same time, an input of the voice recognition reliability of the voice recognition result is received, and the received voice recognition reliability is output to the reliability integration unit 21.
- the machine translation unit 13 translates the input original text (step S301).
- the machine translation unit 13 performs a translation process on the input original sentence from the first language that is the original language to the second language that is the other language specified, and reversely translates the translation result To the unit 14.
- the reverse translation unit 14 performs reverse translation on the translation that is the translation result of the machine translation unit 13 (step S302).
- the reverse translation unit 14 executes a translation process from the second language, which is the translated language, to the first language, which is the original language, again on the translation that is the translation result input from the machine translation unit 13.
- the reverse translation result, which is the translation result is output to the translation reliability calculation unit 15.
- the translation reliability calculation unit 15 calculates the reliability (step S303).
- the translation reliability calculation unit 15 uses the original text described in the first language before translation input via the speech result input unit 210 and the reverse translation translated into the first language again by the reverse translation unit 14. The result is input, and the distance between the two is calculated as the translation reliability. In the present embodiment, the translation reliability calculated here is simply handled as the reliability for the translation processing result.
- the reliability integration unit 21 integrates the speech recognition reliability, which is the reliability of the original text recognition process, and the translation reliability (step S304).
- the reliability integration unit 21 integrates the speech recognition reliability input from the speech recognition result input unit 210 and the translation reliability input from the translation reliability calculation unit 15 by, for example, linear interpolation.
- the reliability to be integrated may be a sentence unit or a word or a word string unit.
- the reliability calculation device 10d outputs the result (step S305).
- the reliability calculation device 10d outputs the integrated reliability obtained by the reliability integration unit 21 via the output unit 12 such as a display and displays it to the user.
- the reliability calculation apparatus 10d may output the reverse translation result together with the integrated reliability.
- the speech recognition reliability and the translation result reliability used to calculate the integrated reliability may be output as additional information.
- the reliability is low, presenting the reverse translation result and reliability together, even if the user who entered the original text cannot understand the second language to be translated, As a result, it is possible to check the result and to estimate the cause and location of the low reliability, and to rephrase or rephrase the portion. Furthermore, in the present embodiment, since reliability can be given in units of words, by emphasizing and presenting a sentence expression for the reverse translation corresponding to the word that has become low reliability, The result can be confirmed more easily, and as a result, the cause of the low reliability and the location can be estimated more easily, and the portion can be rephrased and rephrased.
- the speech translation system 200 illustrated in FIG. 10 includes a speech input unit 211, a speech recognition unit 212, a reliability calculation unit 10d, a result determination unit 220, and an output unit 12.
- the speech translation system 200 is realized by, for example, a general-purpose computer system that includes a CPU, a RAM, a ROM, and a nonvolatile storage device. That is, the CPU may be configured to read a speech translation program in which the operations of the speech recognition unit 212, the reliability calculation unit 10d, and the result determination unit 220 are described in a program language, and execute the speech translation process according to the read program. .
- the speech translation system 200 does not have to be a single computer system, and may be configured by a plurality of computer systems. In such a configuration, the speech translation system 200 receives the speech of the first language that is the original sentence to be translated, translates the sentence or sentence represented by the speech into the second language, and trusts the translation result. Output with degrees.
- the voice input unit 211 receives the first language voice input to the system and outputs it to the voice recognition unit 211.
- a microphone as an input device may be used.
- the voice recognition unit 210 performs voice recognition processing on the voice input via the voice input unit 211, and outputs a voice recognition result and a voice recognition reliability that is a reliability level to the reliability calculation unit 10d.
- the reliability calculation unit 10d accepts the speech recognition result from the speech recognition unit 210 and the input of the reliability as the original text to be translated and the reliability of the original text, and the translation process, the calculation process of the translation reliability and the integrated reliability, I do.
- the reliability calculation unit 10d corresponds to the reliability calculation device 10d shown in FIG. Therefore, only operations different from those in FIG. 8 will be described below, and description of the same operations as those in the configuration in FIG. 8 will be omitted.
- the reliability calculation unit 10d of this example has a configuration equivalent to the reliability calculation device 10e of FIG. 10, and further includes a synonym expansion unit 161 and a synonym dictionary 162 as shown in FIG. Also good.
- the machine translation unit 13 translates the first language into the second language, that is, the translation, not only to the reverse translation unit 14 but also to the result determination unit 220.
- the reliability integration unit 21 outputs the integrated reliability to the result determination unit 220.
- the result determination unit 220 determines whether the translation of the translation result input from the machine translation unit 13 should be output according to the reliability input from the reliability integration unit 21, that is, the integrated reliability.
- the output unit 12 outputs a translation that is a translation result obtained from the result determination unit 220.
- the translated text that is, the text written in the second language may be displayed on the screen, or may be read out by voice using a speaker incorporating a voice synthesizer for outputting the text as voice.
- the output unit 12 does not need to output anything when the result determination unit 220 rejects the translation result, and outputs the reverse translation result and the reliability together with a message indicating that the result is rejected. Also good.
- FIG. 12 is a flowchart showing an example of a processing flow of translation processing in the second embodiment of the present invention.
- the speech translation system 200 inputs speech in the first language (step S400). Specifically, the speech translation system 200 accepts the first language speech input via the speech input unit 211 and outputs it to the speech recognition unit 212.
- the speech translation system 200 recognizes the input speech (step S401). Specifically, in the speech translation system 200, the speech recognition unit 212 performs speech recognition processing on the speech input from the speech input unit 211, and obtains speech recognition results and speech recognition reliability that is reliability. The obtained voice recognition result and the voice recognition reliability are output to the reliability calculation unit 10d. Note that a speech recognition processing method for inputting speech and outputting text as a speech recognition result, and a method for calculating the reliability of the speech recognition result at that time are well known in the art. Therefore, detailed description is omitted here. In the speech reliability calculation unit 10d, the speech recognition result is output to at least the machine translation unit 13 and the translation reliability calculation unit 15, the obtained speech recognition result is output, and the speech recognition result is output to the reliability integration unit 21. Is done.
- the speech translation system 200 translates the speech recognition result (step S402). Specifically, the speech translation system 200 translates the text of the speech recognition result input from the speech recognition unit 212 by the machine translation unit 13, and outputs the translation result to the reverse translation unit 14 and the result determination unit 220.
- the speech translation system 200 performs reverse translation (step S403). Specifically, the speech translation system 200 performs reverse translation processing on the first language again by the reverse translation unit 14 on the translation result obtained by the machine translation unit 13.
- the speech translation system 200 calculates translation reliability (step S404). Specifically, in the translation reliability calculation unit 15 of the speech translation system 200, the original sentence described in the first language before translation, which is the speech recognition result by the speech recognition unit 212, and the reverse translation unit 14 again The reverse translation result translated into one language is input, and the distance between the two is calculated as the translation reliability.
- the translation reliability calculated here is the reliability for the translation process.
- the speech translation system 200 integrates reliability (step S405).
- the reliability integration unit 21 integrates the input speech recognition reliability and the translation reliability by, for example, linear interpolation to obtain a final reliability for the translation result. .
- FIG. 13 is an explanatory diagram showing an example of calculation of reliability in this embodiment.
- the speech recognition result is “what would you like to drink” Since the speech recognition reliability is completely correct, it is assumed that it is 0.99 in units of sentences (entire utterances).
- the translation result into Japanese, which is the second language, based on the speech recognition result is “What do you want to drink (nani wo nomitaidesuka)” and the reverse translation result is “What would you like to drink? ”.
- the translation reliability was 1.0 because the original text whose reverse translation result was the speech recognition result was completely reproduced. In such a case, when these speech recognition reliability and translation reliability are linearly interpolated with a constant weight, the integrated reliability is 0.99.
- the speech recognition result is “you can check into wars before” for the input sentence “you can check in two hours before the departure time” in the first language. the departure time ”, and the speech recognition reliability includes an error, and is 0.79.
- the translation result into Japanese, which is the second language, using the speech recognition result as the original text is “You can check the war before the departure time (shuppatsu jikoku no mae ni sensou wo check dekimasu)” and its reverse translation Suppose the result is "I can check a war before the departure time.”
- the translation reliability is 0.67 because the reverse translation result includes an error, unlike the original text in which the speech recognition result is obtained. In such a case, when these speech recognition reliability and translation reliability are linearly interpolated with a constant weight, the integrated reliability is 0.77.
- the speech recognition result is “I'll walk to the bank”. It is assumed that the voice recognition reliability is 0.64.
- the translation result into the second language, Chinese using the speech recognition result as the original text is as shown in the figure, and the reverse translation result is “I'll walk to the bank”.
- the translation reliability was 1.0, which is a complete reproduction of the original text whose reverse translation result is the speech recognition result. In such a case, if these speech recognition reliability and translation reliability are linearly interpolated with a constant weight, the integrated reliability is 0.71.
- the speech recognition result is “do you have chairs for children” for the input sentence “um do you have chairs for children” in the first language, English.
- the voice recognition reliability is 0.94.
- the result of translation into the second language, Chinese using the speech recognition result as the original text is as shown in the figure, and the reverse translation result is “IsIthere a lecture of a child?”.
- the translation reliability was set to 0.0 because the reverse translation result was different from the original sentence that was the speech recognition result and contained an error. In such a case, when these speech recognition reliability and translation reliability are linearly interpolated with a constant weight, the integrated reliability is 0.75.
- the speech translation system 200 performs a result determination (step S406). Specifically, the speech translation system 200 determines whether the result determination unit 220 should output the translation of the translation result input from the machine translation unit 13 according to the integrated reliability input from the reliability integration unit 21. Judgment.
- both the speech recognition result and the machine translation result are correct, and the integrated reliability (denoted as speech translation reliability in the figure) is as high as 0.99. judge.
- both the speech recognition result and the machine translation result include an error, and the integrated reliability is not sufficiently high as 0.77 (specifically, it is lower than a predetermined threshold). ), It is determined that it is rejected, that is, output is impossible.
- the machine translation result is correct but the speech recognition result includes an error.
- the speech recognition is almost correct but the translation result includes an error. Also in the example, since the integrated reliability is not sufficiently high as 0.77, it is determined that rejection, that is, output is impossible.
- the speech translation system 200 outputs the result (step S407). Specifically, the speech translation system 200 outputs the translation result obtained as a result of the determination by the result determination unit 220 via the output unit 12, thereby displaying the result on a display or the like, for example.
- the reliability presentation unit 17 receives the reverse translation result obtained by the reverse translation unit 14 and the reliability obtained by the reliability integration unit 21.
- the reliability submission unit 17 receives the reverse translation result obtained by the reverse translation unit 14 and the reliability obtained by the reliability integration unit 21.
- the reliability presented by the reliability presentation unit 17 at this time does not have to be in units of sentences (or the entire utterance), and may be presented in units of words, for example. This may make it easier to identify the paraphrase. In that case, the integration of the speech recognition reliability and the translation reliability in the reliability integration unit 21 may be first performed for each word and then expanded for each sentence.
- FIG. 14 is a block diagram showing an outline of the present invention.
- the reliability calculation apparatus includes a translation unit 501, a reverse translation unit 502, a translation reliability calculation unit 503, and a reliability presentation unit 504.
- the translation unit 501 (for example, the machine translation unit 13) performs a translation process on the input sentence into a second language that is different from the first language that is the language of the input sentence.
- the reverse translation unit 502 (for example, the reverse translation unit 14) performs reverse translation processing on the translation result obtained as a result of translation processing by the translation unit 501 into the first language that is the language of the input sentence.
- the translation reliability calculation unit 503 calculates the translation reliability based on the distance between the input sentence and the reverse translation result obtained as a result of the reverse translation process by the reverse translation unit 502.
- the reliability presentation unit 504 corresponds to at least one of the input sentence, the translation result, and the reverse translation result to the input sentence, the translation result, or the reverse translation result. Present to the user along with the reliability. At that time, if the translation reliability is equal to or less than a predetermined threshold, at least the input sentence or the reverse translation result is presented to the user who has input the first language together with the translation reliability.
- the “reliability corresponding to the (presented) word or word string” refers to, for example, when the original text or the reverse translation result is presented, the word or word string is compared with the original text and the reverse translation result. It is the integrated reliability that combines the calculated translation reliability and the translation reliability and the recognition reliability. Further, for example, when presenting a translation result, the translation reliability or the integrated reliability calculated for the original sentence word or word string that was used when the word or word string was translated.
- the reliability calculation apparatus converts a text, which is a result of performing recognition processing on a sentence or sentence data input by a method other than text input such as voice input, as an input sentence to the translation unit 501.
- the integrated reliability calculation means for calculating the integrated reliability using the reliability of the recognition process for the input sentence and the translation reliability calculated by the translation reliability calculation means 503. may be provided.
- the reliability presentation unit 504 outputs at least the input sentence or the reverse translation result together with the integrated reliability or the translation reliability as the first language. You may show to the user of the input side.
- the translation reliability calculation means 503 may obtain the distance between the input sentence and the reverse translation result by the reverse translation means using the shared N-gram.
- the translation reliability calculation means 503 may obtain the translation reliability in units of words or word strings, and may obtain the translation reliability in units of sentences by normalization.
- the reliability presenting means 504 outputs at least the input sentence or the reverse translation result for each of the input sentence or the reverse translation result. You may show to the user who input the 1st language with the reliability corresponding to a word or a word string.
- the reliability degree presentation unit 504 corresponds to each word or word string of the input sentence, the translation result, or the reverse translation result when presenting at least one of the input sentence, the translation result, and the reverse translation result to the user.
- the low confidence interval in one sentence may be emphasized and presented based on the confidence level.
- the reliability calculation device further includes synonym expansion means (for example, synonym expansion unit 161 and synonym dictionary 162) that performs synonym expansion on at least one of the input sentence and the reverse translation result. You may have.
- the translation reliability calculation unit 503 may calculate the distance for each combination of the input sentence after the synonym expansion and the reverse translation result, and calculate the translation reliability based on the calculated distance.
- the synonym expansion means may perform synonym expansion only for words or word strings that are commonly held in the recognition dictionary used in the recognition process and the translation dictionary used in the translation process and the reverse translation process. .
- a translation unit that performs translation processing into a second language that is different from the first language that is the language of the input sentence, and a translation result obtained as a result of the translation process
- the translation reliability based on the distance between the reverse translation unit that performs the reverse translation process to the first language that is the language of the input sentence, and the reverse translation result obtained as a result of the reverse translation process, the translation reliability And a reliability of presenting at least one or more of the input sentence, the translation result and the reverse translation result together with a reliability corresponding to the input sentence, the translation result or the reverse translation result to the user.
- a presentation unit and when the translation reliability is less than or equal to a predetermined threshold, the reliability presentation unit inputs at least the input sentence or the reverse translation result together with the translation reliability to the first language.
- a reliability calculation device that uses a text that is a result of recognition processing for sentence or sentence data in a first language input by a method other than text input, as an input sentence to the translation unit.
- the integrated reliability calculation unit for calculating the integrated reliability the reliability presentation unit is When the integrated reliability is equal to or lower than a predetermined threshold, at least the input sentence or the reverse translation result is presented to the user who has input the first language together with the integrated reliability or the translation reliability.
- Additional remark 3 The reliability calculation apparatus of Additional remark 1 or Additional remark 2 which a translation reliability calculation part calculates
- the translation reliability calculation unit obtains the translation reliability in units of words or word strings and obtains the translation reliability in units of sentences by normalization, and the reliability presentation unit has the integrated reliability or the translation reliability. If it is less than or equal to a predetermined threshold, at least the input sentence or reverse translation result is sent to the user who has input the first language together with the reliability corresponding to each word or word string of the input sentence or reverse translation result.
- the reliability calculation apparatus according to any one of Supplementary Note 1 to Supplementary Note 3 to be presented.
- a reliability presentation part shows a 1st language to a user at least 1 or more among an input sentence, a translation result, and a back translation result, each of the said input sentence, a translation result, or a back translation result
- the reliability calculation apparatus according to appendix 4, wherein the low reliability interval in one sentence is emphasized and presented based on the reliability corresponding to the word or the word string.
- a synonym expansion unit that performs synonym expansion on at least one of the input sentence and the reverse translation result is provided, and the translation reliability calculation unit is configured to display the input sentence after the synonym expansion and the reverse translation result
- the reliability calculation apparatus according to any one of appendix 1 to appendix 5, which calculates a distance for each combination and calculates a translation reliability based on the calculated distance.
- the present invention is not limited to a translation device that performs a translation process on a sentence or sentence input in a text data format, but also a speech input or a sentence or sentence data input using an OCR or a touch panel, and a recognition process.
- the present invention can also be suitably applied to a translation apparatus that performs translation processing after passing through.
- Reliability presentation unit 100 machine translation device 110, 220 result determination unit 200 speech translation system 210 speech recognition result input unit 211 speech input unit 212 speech recognition unit 21 reliability integration unit 501 translation unit 502 reverse translation unit 503 translation reliability calculation unit 504 Reliability presentation means
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Machine Translation (AREA)
Abstract
The present invention makes it possible to suitably achieve reliability in translation results in a machine translation, even without presupposition of a statistical machine translation, and to suitably prompt re-entry to the input-side user if the reliability is low. The present invention is characterized in being provided with: a translation means (501) for performing machine translation on inputted text; a reverse translation means (502) for performing a reverse translation process on the translation result; a translation reliability computation means (503) for calculating translation reliability on the basis of the distance between the inputted text and the reverse translation result; and a reliability presentation means (504) for presenting the user with one or more of the inputted text, the translation result, and the reverse translation result together with the reliability corresponding to the inputted text, the translation result, or the reverse translation result, wherein the reliability presentation means (504) presents the inputted text and/or the reverse translation result together with the translation reliability to the user, on the side in which a first language was inputted, when the translation reliability is equal to or less than a predetermined threshold value.
Description
本発明は、機械翻訳や音声翻訳の信頼度を求める信頼度算出装置、信頼度算出利用方法および翻訳エンジン用プログラムに関する。
The present invention relates to a reliability calculation device for determining the reliability of machine translation and speech translation, a reliability calculation usage method, and a program for a translation engine.
近年、第一の言語で記述されたテキストなどの文字情報を、異なる第二の言語に変換する機械翻訳の技術の実用化が盛んである。また、テキストの代わりに音声を入力とし、音声認識結果を機械翻訳の入力として用いる音声翻訳技術も実用化が始まっている。
In recent years, machine translation technology for converting character information such as text described in a first language into a different second language has been put into practical use. In addition, speech translation technology that uses speech instead of text as input and uses speech recognition results as input for machine translation has been put into practical use.
このような機械翻訳や音声翻訳システムを利用すれば、異なる言語を持つ者同士がコミュニケーションを行うことが可能になるため、本技術に対する期待は高い。一方で、音声認識や機械翻訳の技術は完全でなく、結果に誤認識や誤翻訳を含むことがある。誤認識・誤翻訳を含む結果を相手に提示してしまうと、コミュニケーションが破綻していく恐れがあるが、最終的な翻訳結果の妥当性を話し手であるユーザ自身が判断するのは一般に困難である。
Using such machine translation and speech translation systems, people with different languages can communicate with each other, so there is high expectation for this technology. On the other hand, speech recognition and machine translation techniques are not perfect, and results may include misrecognition and mistranslation. If the result including misrecognition and mistranslation is presented to the other party, communication may be disrupted, but it is generally difficult for the user who is the speaker himself to judge the validity of the final translation result. is there.
このため、音声認識結果や翻訳結果にシステム側から確信度や信頼度といった数値を付与する試みがなされている。音声認識結果や翻訳結果に信頼度が付与されると、低信頼度の発話・入力を棄却することでコミュニケーションの破綻を回避したり、低信頼度の部分を話し手側が言い換えることで正しい結果に近づけることが可能となる。
For this reason, attempts have been made to assign numerical values such as confidence and reliability from the system side to the speech recognition results and translation results. When reliability is given to speech recognition results and translation results, communication failures can be avoided by rejecting low-confidence utterances / inputs, or a speaker can rephrase the low-reliability part to bring it closer to the correct result. It becomes possible.
例えば、機械翻訳の出力訳文候補の選択装置において、順位和に基づく信頼度(RSCM)を用いる方法が特許文献1に記載されている。この方法は、統計的機械翻訳(Statistic Machine Translation :SMT)が出力する上位N個の訳文候補(N-best)のうち、各訳文候補である仮説の順位に基づいて各N-bestの先頭仮説の単語の事後確率を算出し、信頼度を求めるものである。
For example, Patent Document 1 discloses a method of using reliability (RSCM) based on the sum of ranks in a machine translation output candidate selection apparatus. This method is based on the top hypothesis of each N-best based on the ranking of hypotheses that are translation candidates among the top N translation candidates (N-best) output by statistical machine translation (Statistic Machine Translation: SMT). The posterior probability of the word is calculated and the reliability is obtained.
また、特許文献2には、第1の言語による参照テキストから第2の言語によるテキストへの機械翻訳を行う場合に、変換後の第2の言語によるテキストを、第1の言語による折り返し翻訳テキストに逆変換して、翻訳前の参照テキストと逆変換後の第1の言語によるデータとの類似度を変換適正値とするデータ変換適正評価方法が記載されている。
Further, in Patent Document 2, when machine translation from a reference text in a first language into a text in a second language is performed, the translated text in the second language is converted into a folded translation text in the first language. A data conversion appropriate evaluation method is described in which the similarity between the reference text before translation and the data in the first language after reverse conversion is converted into an appropriate conversion value.
また、特許文献3には、入力される第1の言語の音声に対して、音声認識および第2の言語への機械翻訳を行う機械翻訳システムにおいて、音声認識モジュールから出力されるNベストの仮説とそれらの情報と、統計的機械翻訳モジュールから出力されるNベスト仮説の各々に対するK個の訳文候補とそれらに付随する情報とに基づいて、N×K個の訳文候補各々を再スコアして、最も高いスコアを達成する訳文をベスト訳文として出力する再スコアリングモジュールを備える構成が記載されている。
Patent Document 3 discloses the N best hypothesis output from a speech recognition module in a machine translation system that performs speech recognition and machine translation into a second language for input speech in a first language. And re-scoring each of N × K translation candidates based on the K translation candidates for each of the N best hypotheses output from the statistical machine translation module and the information associated therewith. A configuration including a rescoring module that outputs a translation that achieves the highest score as the best translation is described.
しかし、特許文献1に記載されている方法は、翻訳処理として統計的機械翻訳を用いることが前提となっている。このため、文法ベース(ルールベース)で翻訳処理を行う文法規則型翻訳を用いる場合には適用できない。文法規則型翻訳においては尤度という概念が明確でないからである。なお、現在、一般には統計的機械翻訳よりも文法規則型翻訳の方がより高精度な翻訳が実現できると考えられている。
However, the method described in Patent Document 1 is based on the premise that statistical machine translation is used as a translation process. For this reason, it is not applicable when using grammatical rule type translation that performs translation processing on a grammar base (rule base). This is because the concept of likelihood is not clear in grammatical rule translation. Currently, it is generally considered that grammatical rule-based translation can achieve more accurate translation than statistical machine translation.
また、特許文献1に記載されている方法は、機械翻訳の処理結果に対してのみ信頼度を付与するものである。従って、機械翻訳において入力側の文章に不明瞭な部分があった場合等に、入力側の言語を持つユーザに適切に再入力を促すことができない。また、音声で入力される文章に対して音声認識を行った上で機械翻訳を行う場合などにおいて、原文の一部の表現を変えれば最終的に正しく翻訳される可能性がある場合に、機械翻訳の処理結果に対する信頼度だけでは、入力する側のユーザが原文を再入力すべきか否かの判断を行うことは困難である。
Also, the method described in Patent Document 1 gives reliability only to the processing result of machine translation. Therefore, when there is an unclear part in the input-side sentence in machine translation, it is not possible to prompt the user who has the input-side language to appropriately input again. In addition, when performing machine translation after performing speech recognition on a sentence that is input in speech, if there is a possibility that it will eventually be translated correctly if part of the original sentence is changed, It is difficult for the user on the input side to determine whether or not to re-input the original text only with the reliability of the translation processing result.
なお、特許文献2に記載されている方法を利用すれば、機械翻訳として統計的機械翻訳を前提としなくても、機械翻訳の信頼度を得ることはできる。しかし、特許文献2に記載されている方法は、機械翻訳の処理結果に対してのみ信頼度を付与するものであるので、特許文献1と同様、入力側の言語を持つユーザに適切に再入力を促すことができないという問題がある。
If the method described in Patent Document 2 is used, the reliability of machine translation can be obtained without assuming statistical machine translation as machine translation. However, since the method described in Patent Document 2 gives reliability only to the processing result of machine translation, as in Patent Document 1, it is appropriately re-input to a user having an input language. There is a problem that cannot be urged.
また、特許文献3に記載されている方法は、音声認識モジュールと機械翻訳モジュールとから得られる特徴量(例えば、それぞれの精度を反映した尤度情報)を組み合わせて、N×K個の訳文候補の各々にスコアを割り当てるので、翻訳処理の結果のみならず音声認識処理の結果をも考慮した、より高い信頼度をもった翻訳結果を得ることができるかもしれない。しかし、特許文献3に記載されている方法は、機械翻訳として統計的機械翻訳を前提としている。また、再スコアリングされたスコアを複数の訳文候補からベスト訳文を選定するために用いることしか想定していない。このため、モデリングすることにより一本化して算出される評価はどこに問題点があるのかがわかりにくく、信頼度を元にユーザに適切に再入力を促すことはできない。
In addition, the method described in Patent Document 3 combines N × K translation candidate candidates by combining feature amounts (for example, likelihood information reflecting each accuracy) obtained from the speech recognition module and the machine translation module. Since a score is assigned to each of these, it may be possible to obtain a translation result with higher reliability in consideration of not only the result of translation processing but also the result of speech recognition processing. However, the method described in Patent Document 3 assumes statistical machine translation as machine translation. Further, it is only assumed that the re-scored score is used to select the best translation from a plurality of translation candidates. For this reason, it is difficult to understand where the problem is in the evaluation that is calculated by unifying by modeling, and it is not possible to prompt the user to appropriately input again based on the reliability.
そこで、本発明は、機械翻訳として統計的機械翻訳を前提としなくても、適切に翻訳結果に対する信頼度を得ることができ、かつ低信頼度であった場合に入力側ユーザに適切に再入力を促すことができる信頼度算出装置、翻訳信頼度算出利用方法および翻訳エンジン用プログラムを提供することを目的とする。ここで、翻訳結果に対する信頼度は、音声等のテキストデータ以外の方法により入力される場合においては、入力された第一の言語による文または文章データ(例えば、音声データ)に対して第一の言語による認識処理を経て行われる機械翻訳の最終的な処理結果に対する信頼度をいう。すなわち、単純に機械翻訳処理の処理結果だけでなく、その前段階の認識処理の処理結果をも考慮した信頼度をいう。
Therefore, the present invention can appropriately obtain the reliability of the translation result without assuming statistical machine translation as the machine translation, and appropriately re-input to the input side user when the reliability is low. An object of the present invention is to provide a reliability calculation device, a translation reliability calculation usage method, and a translation engine program. Here, in the case where the reliability for the translation result is input by a method other than text data such as speech, the reliability is the first for the sentence or sentence data (for example, speech data) in the input first language. This refers to the reliability of the final processing result of machine translation performed through language recognition processing. That is, it means the reliability considering not only the processing result of the machine translation process but also the processing result of the preceding recognition process.
本発明による信頼度算出装置は、入力文に対して、入力文の言語である第一の言語とは異なる言語である第二の言語への翻訳処理を行う翻訳手段と、翻訳手段による翻訳処理の結果得られる翻訳結果に対して、入力文の言語である第一の言語への逆翻訳処理を行う逆翻訳手段と、入力文と逆翻訳手段による逆翻訳処理の結果得られる逆翻訳結果との距離に基づいて、翻訳信頼度を算出する翻訳信頼度計算手段と、入力文、翻訳結果および逆翻訳結果のうち少なくとも1つ以上を、当該入力文、翻訳結果または逆翻訳結果に対応する信頼度とともにユーザに提示する信頼度提示手段とを備え、信頼度提示手段は、翻訳信頼度が所定の閾値以下であった場合には、少なくとも入力文または逆翻訳結果を、翻訳信頼度とともに第一の言語を入力した側のユーザに提示することを特徴とする。
The reliability calculation apparatus according to the present invention includes a translation unit that performs translation processing on an input sentence into a second language that is different from the first language that is the language of the input sentence, and translation processing that is performed by the translation unit A reverse translation means for performing a reverse translation process to the first language which is the language of the input sentence, and a reverse translation result obtained as a result of the reverse translation process by the input sentence and the reverse translation means. A translation reliability calculation means for calculating a translation reliability based on the distance between the input sentence, the translation result, and the reverse translation result, at least one of the input sentence, the translation result, and the reverse translation result. A reliability presenting means for presenting to the user together with the degree of reliability, and the reliability presenting means first outputs at least the input sentence or the reverse translation result together with the translation reliability when the translation reliability is below a predetermined threshold. Enter the language of Characterized in that it presents on the part of the user.
また、本発明による翻訳信頼度算出利用方法は、入力文に対して、入力文の言語である第一の言語とは異なる言語である第二の言語への翻訳処理を行い、翻訳処理の結果得られる翻訳結果に対して、入力文の言語である第一の言語への逆翻訳処理を行い、入力文と逆翻訳処理の結果得られる逆翻訳結果との距離に基づいて、翻訳信頼度を算出し、入力文、翻訳結果および逆翻訳結果のうち少なくとも1つ以上を、当該入力文、翻訳結果または逆翻訳結果に対応する信頼度とともに第一の言語を入力した側のユーザに提示する際に、翻訳信頼度が所定の閾値以下であった場合には、少なくとも入力文または逆翻訳結果を、翻訳信頼度とともに第一の言語を入力した側のユーザに提示することを特徴とする。
The translation reliability calculation and utilization method according to the present invention performs a translation process on an input sentence into a second language that is different from the first language that is the language of the input sentence, and results of the translation process The translation result is reverse translated into the first language, which is the language of the input sentence, and the translation reliability is determined based on the distance between the input sentence and the reverse translation result obtained as a result of the reverse translation process. When calculating and presenting at least one of the input sentence, translation result and reverse translation result to the user who has input the first language together with the reliability corresponding to the input sentence, translation result or reverse translation result In addition, when the translation reliability is equal to or lower than a predetermined threshold, at least the input sentence or the reverse translation result is presented to the user who has input the first language together with the translation reliability.
また、本発明による翻訳エンジン用プログラムは、コンピュータに、第一の言語で記述された入力文を、第一の言語とは異なる言語である第二の言語に変換する翻訳処理、翻訳処理の結果得られる翻訳結果を、入力文の言語である第一の言語に変換する逆翻訳処理、入力文と逆翻訳処理の結果得られる逆翻訳結果との距離に基づいて、翻訳信頼度を算出する翻訳信頼度算出処理、および入力文、翻訳結果および逆翻訳結果のうち少なくとも1つ以上を、当該入力文、翻訳結果または逆翻訳結果に対応する信頼度とともにユーザに提示する信頼度提示処理を実行させ、信頼度提示処理で、翻訳信頼度が所定の閾値以下であった場合に、少なくとも入力文または逆翻訳結果を、翻訳信頼度とともに第一の言語を入力した側のユーザに提示させることを特徴とする。
Further, the translation engine program according to the present invention includes a computer, a translation process for converting an input sentence described in a first language into a second language that is a language different from the first language, and a result of the translation process. Translation that calculates translation reliability based on the distance between the reverse translation process that converts the obtained translation result into the first language that is the language of the input sentence, and the reverse translation result that is obtained as a result of the reverse translation process A reliability calculation process and a reliability presentation process for presenting at least one of the input sentence, the translation result, and the reverse translation result together with the reliability corresponding to the input sentence, the translation result, or the reverse translation result to the user. In the reliability presentation process, if the translation reliability is equal to or lower than a predetermined threshold, at least the input sentence or the reverse translation result is presented to the user who has input the first language together with the translation reliability. And wherein the door.
本発明によれば、機械翻訳として統計的機械翻訳を前提としなくても、適切に翻訳結果に対する信頼度を得ることができ、かつ低信頼度であった場合に入力側ユーザに適切に再入力を促すことができる。
According to the present invention, even if statistical machine translation is not premised on machine translation, the reliability of the translation result can be appropriately obtained, and when the reliability is low, the input user is appropriately re-input Can be encouraged.
以下、本発明の実施形態を図面を参照して説明する。
Hereinafter, embodiments of the present invention will be described with reference to the drawings.
実施形態1.
図1は、本発明の第1の実施形態の信頼度算出装置の構成例を示したブロック図である。図1に示す信頼度算出装置10は、テキストまたは文字列を入力し、機械翻訳を行うとともにその信頼度を算出して出力するものである。Embodiment 1. FIG.
FIG. 1 is a block diagram showing a configuration example of a reliability calculation apparatus according to the first embodiment of the present invention. Thereliability calculation apparatus 10 shown in FIG. 1 inputs text or a character string, performs machine translation, calculates the reliability, and outputs it.
図1は、本発明の第1の実施形態の信頼度算出装置の構成例を示したブロック図である。図1に示す信頼度算出装置10は、テキストまたは文字列を入力し、機械翻訳を行うとともにその信頼度を算出して出力するものである。
FIG. 1 is a block diagram showing a configuration example of a reliability calculation apparatus according to the first embodiment of the present invention. The
信頼度算出装置10は、機械翻訳部13と、逆翻訳部14と、翻訳信頼度計算部15とを備えている。また、信頼度算出装置10は、この他に直接または間接的に、入力部11と出力部12とを備えているものとする。なお、「間接的に」とは、例えば、ネットワークを介して接続される他の装置が備えていてもよいことを意味している。
The reliability calculation device 10 includes a machine translation unit 13, a reverse translation unit 14, and a translation reliability calculation unit 15. In addition, the reliability calculation apparatus 10 includes an input unit 11 and an output unit 12 directly or indirectly. Note that “indirectly” means, for example, that other devices connected via a network may be provided.
信頼度算出装置10は、例えば、図示しないCPU、RAM、ROM及び不揮発性記憶装置を備えた汎用的なコンピュータシステムであってもよい。すなわち、信頼度算出装置10は、CPU等の情報処理装置が、RAM、ROMまたは不揮発性記憶装置に記憶されたOSおよび信頼度算出プログラムを読み込んで、信頼度算出処理を含む所定の処理を実行するよう構成されていてもよい。これにより、翻訳結果の信頼度を出力することができる。なお、信頼度算出装置10は、一台のコンピュータシステムである必要はなく、複数台のコンピュータで構成されていてもよい。
The reliability calculation device 10 may be, for example, a general-purpose computer system that includes a CPU, RAM, ROM, and non-volatile storage device (not shown). That is, in the reliability calculation device 10, an information processing device such as a CPU reads an OS and a reliability calculation program stored in a RAM, a ROM, or a non-volatile storage device, and executes predetermined processing including reliability calculation processing. It may be configured to. Thereby, the reliability of a translation result can be output. In addition, the reliability calculation apparatus 10 does not need to be one computer system, and may be configured by a plurality of computers.
入力部11は、信頼度算出装置10に対して、翻訳前の第一の言語で記述された文すなわち原文を入力するキーボード等である。なお、入力部11は、原文をどの言語に翻訳するかを示す指示情報を入力してもよい。また、出力部12は、信頼度算出装置10から出力される信頼度をユーザに表示するディスプレイ等である。
The input unit 11 is a keyboard or the like for inputting a sentence described in a first language before translation, that is, an original sentence, to the reliability calculation apparatus 10. Note that the input unit 11 may input instruction information indicating in which language the original sentence is translated. The output unit 12 is a display or the like that displays the reliability output from the reliability calculation device 10 to the user.
機械翻訳部13は、入力された原文を、翻訳後の第二の言語の文すなわち訳文に翻訳する。なお、翻訳技術として用いる手法は、統計的機械翻訳でもよいし、文法規則型翻訳でもよいし、用例ベース翻訳でもよい。翻訳技術自体は、公知技術としてよく知られているものであるから、ここでは詳細な説明を省略する。
The machine translation unit 13 translates the input original sentence into a translated second language sentence, that is, a translated sentence. The technique used as the translation technique may be statistical machine translation, grammatical rule translation, or example-based translation. Since the translation technique itself is well known as a known technique, a detailed description thereof is omitted here.
逆翻訳部14は、機械翻訳部13によって翻訳された訳文を入力とし、入力された訳文を元の第一の言語に翻訳する。ここでの翻訳手法は、機械翻訳部13における翻訳手法と異なる手法を用いてもよいが、同じ手法を用いる方が一般には平易である。
The reverse translation unit 14 receives the translation translated by the machine translation unit 13 and translates the input translation into the original first language. The translation method here may be a method different from the translation method in the machine translation unit 13, but it is generally easier to use the same method.
翻訳信頼度計算部15は、翻訳前の第一の言語で記述された原文と、逆翻訳部14によって再び第一の言語に翻訳された逆翻訳結果とを入力とし、入力された原文と逆翻訳結果との距離を求めて、信頼度とする。以下、翻訳信頼度計算部15が算出する信頼度(具体的には、機械翻訳部13の翻訳処理結果に対する信頼度)を翻訳信頼度という。なお、本実施形態では、ここで算出される翻訳信頼度をそのまま翻訳結果に対する信頼度として扱う。
The translation reliability calculation unit 15 receives the original text described in the first language before translation and the reverse translation result translated into the first language again by the reverse translation unit 14, and reverses the input original text. Find the distance from the translation result and use it as the reliability. Hereinafter, the reliability calculated by the translation reliability calculation unit 15 (specifically, the reliability with respect to the translation processing result of the machine translation unit 13) is referred to as translation reliability. In the present embodiment, the translation reliability calculated here is directly used as the reliability for the translation result.
翻訳信頼度計算部15は、原文と逆翻訳結果との間の距離、すなわち両文の近さを表す所定の尺度による評価値を、例えば共有N-gram数を利用したBLEUスコアによって求めてもよい。なお、BLEUスコアは、統計的機械翻訳の評価を行う際に用いられる尺度であり、ある翻訳結果の文が正解文をどれだけ再現できているかを、両者で共有する単語連鎖(N-gram)の数を利用して求めて、0~1の範囲で出力するものである。BLEUスコアの算出式の一例を以下に式(1)として示す。
The translation reliability calculation unit 15 may obtain an evaluation value based on a predetermined scale representing the distance between the original text and the reverse translation result, that is, the closeness between the two sentences, for example, using a BLEU score using the shared N-gram number. Good. The BLEU score is a scale used in the evaluation of statistical machine translation, and the word chain (N-gram) that is shared by both of how much the sentence of a certain translation result can reproduce the correct sentence. This is obtained using the number of and is output in the range of 0 to 1. An example of a BLEU score calculation formula is shown below as Formula (1).
式(1)において、BPは長さ方向のペナルティを表し、NはN-gramの最大長を表し、wnは結合重み(1/Nでよい)を表し、Pnは修正N-gram精度を表している。なお、修正N-gram精度は、共有N-gram数の最大値を全体のN-gram数で除算したものである。なお、BLEUスコアは、文が短い場合に低精度になるという課題があるが、後述するような音声認識の信頼度など他の尺度と組み合わせることで、精度を上げることができる。また、ここでは距離としてBLEUスコアを用いる例を示したが、距離の算出方法はこの方法に限らない。
In the formula (1), BP represents a penalty longitudinal, N represents represents the maximum length of the N-gram, w n denotes a coupling weight (which may be 1 / N), P n is modified N-gram accuracy Represents. The modified N-gram accuracy is obtained by dividing the maximum value of the shared N-gram number by the total N-gram number. The BLEU score has a problem that it becomes low accuracy when the sentence is short, but accuracy can be improved by combining with other measures such as reliability of speech recognition as described later. Moreover, although the example which uses a BLEU score as distance was shown here, the calculation method of distance is not restricted to this method.
また、原文と逆翻訳結果との間の距離を単語または単語列単位に求めることも可能である。そのような場合には、単語または単語列単位での距離を求めた後、文全体で正規化するとよい。このように単語または単語列単位に距離すなわち翻訳信頼度を求めることで、一文内での低信頼度区間の提示といったことが可能になる。翻訳信頼度を文単位に拡張する方法としては、得られる単語単位の信頼度を文全体で正規化してもよいし、文全体の信頼度を各単語単位の信頼度の同時確率と捉えてもよい。
It is also possible to obtain the distance between the original text and the reverse translation result in units of words or word strings. In such a case, after obtaining the distance in units of words or word strings, it is preferable to normalize the whole sentence. Thus, by obtaining the distance, that is, the translation reliability in units of words or word strings, it becomes possible to present a low reliability section in one sentence. As a method of extending the translation reliability to the sentence unit, the obtained word unit reliability may be normalized for the whole sentence, or the whole sentence reliability may be regarded as the simultaneous probability of the reliability of each word unit. Good.
以下の式(2)は、文{wn
l}を構成する各単語wiの翻訳信頼度をCMMT(wi)としたとき、単語事後確率を文全体で正規化して翻訳信頼度CMMTを文単位に拡張する場合の計算例である。
The following equation (2) is obtained by normalizing the word posterior probabilities for the entire sentence when the translation reliability of each word w i constituting the sentence {w n l } is CM MT (w i ), and the translation reliability CM. It is a calculation example in the case of extending MT in sentence units.
また、以下の式(3)は、各単語の信頼度を確率事象として捉え、文全体の信頼度をその同時確率として翻訳信頼度CMMTを文単位に拡張する場合の計算例である。
Also, the following equation (3) is a calculation example in the case where the reliability of each word is regarded as a probability event, and the translation reliability CM MT is expanded in sentence units with the reliability of the entire sentence as the joint probability.
なお、逆翻訳による信頼度は翻訳による再現性を表すとも言えるため、信頼度の付与は逆翻訳結果に付与することも翻訳前の原文に付与することも同等の意味を持つ。すなわち、低信頼度区間の提示は、翻訳結果に対してのみならず、入力された原文や逆翻訳結果に対しても行うことが可能である。
In addition, since it can be said that the reliability by reverse translation represents the reproducibility by translation, the assignment of reliability has the same meaning whether it is given to the reverse translation result or the original text before translation. That is, the low confidence interval can be presented not only for the translation result but also for the input original text or reverse translation result.
次に、本実施形態の動作について説明する。以下では、本実施形態の信頼度算出装置10における信頼度算出処理について図2を参照して説明する。図2は、本実施形態の信頼度算出装置10における信頼度算出処理の処理フローの一例を示すフローチャートである。図2に示すように、まず信頼度算出装置10は、翻訳対象の原文となるテキストを入力する(ステップS100)。ここでは、入力部11を介して、第一の言語で記述された文すなわち原文の入力を受け付け、受け付けた原文を機械翻訳部13および翻訳信頼度計算部15に出力する。
Next, the operation of this embodiment will be described. Below, the reliability calculation process in the reliability calculation apparatus 10 of this embodiment is demonstrated with reference to FIG. FIG. 2 is a flowchart illustrating an example of a processing flow of the reliability calculation process in the reliability calculation apparatus 10 of the present embodiment. As shown in FIG. 2, first, the reliability calculation device 10 inputs a text that is an original sentence to be translated (step S <b> 100). Here, the input of the sentence described in the first language, that is, the original sentence is received via the input unit 11, and the received original sentence is output to the machine translation unit 13 and the translation reliability calculation unit 15.
次に、機械翻訳部13が、入力された原文を翻訳する(ステップS101)。機械翻訳部13は、入力された原文に対して、原文の言語である第一の言語から指定された他の言語である第二の言語への翻訳処理を実行し、その翻訳結果を逆翻訳部14に出力する。
Next, the machine translation unit 13 translates the input original text (step S101). The machine translation unit 13 performs a translation process on the input original sentence from the first language that is the original language to the second language that is the other language specified, and reversely translates the translation result To the unit 14.
次に、逆翻訳部14が、機械翻訳部13の翻訳結果である訳文に対して、逆翻訳を行う(ステップS102)。逆翻訳部14は、機械翻訳部13から入力された翻訳結果である訳文に対して、訳文の言語である第二の言語から再び原文の言語である第一の言語への翻訳処理を実行し、その翻訳結果である逆翻訳結果を翻訳信頼度計算部15に出力する。
Next, the reverse translation unit 14 performs reverse translation on the translation that is the translation result of the machine translation unit 13 (step S102). The reverse translation unit 14 executes a translation process from the second language, which is the translated language, to the first language, which is the original language, again on the translation that is the translation result input from the machine translation unit 13. The reverse translation result, which is the translation result, is output to the translation reliability calculation unit 15.
次に、翻訳信頼度計算部15が、信頼度を計算する(ステップS103)。翻訳信頼度計算部15は、入力部11を介して入力された翻訳前の第一の言語で記述された原文と、逆翻訳部14にて再び第一の言語に翻訳された逆翻訳結果とを入力とし、両者の距離を計算して信頼度とする。なお、翻訳信頼度としての距離は、共有N-gramを利用して求めるのが好適であるが、これに限らない。
Next, the translation reliability calculation unit 15 calculates the reliability (step S103). The translation reliability calculation unit 15 includes the original text described in the first language before translation input via the input unit 11 and the reverse translation result translated into the first language again by the reverse translation unit 14. Is input, and the distance between the two is calculated as the reliability. The distance as the translation reliability is preferably obtained using a shared N-gram, but is not limited thereto.
最後に、信頼度算出装置10は、結果を出力する(ステップS104)。信頼度算出装置10は、翻訳信頼度計算部15によって得られた翻訳信頼度を、例えば、ディスプレイ等の出力部12を介して出力してユーザに表示する。このとき、信頼度算出装置10は、翻訳信頼度とともに逆翻訳結果を出力してもよい。
Finally, the reliability calculation device 10 outputs the result (step S104). The reliability calculation device 10 outputs the translation reliability obtained by the translation reliability calculation unit 15 via the output unit 12 such as a display and displays it to the user. At this time, the reliability calculation device 10 may output the reverse translation result together with the translation reliability.
なお、上実施形態では、原文と逆翻訳結果との距離を計算する際に、両者の距離を計算するとしたが、このとき、原文および逆翻訳結果とを同義語展開してもよい。例えば、図3に示す信頼度算出装置10bのように、さらに同義語展開部161と、同義語辞典162とを備えていてもよい。なお、図3は、本実施形態の信頼度算出装置の他の構成例を示すブロック図である。
In the above embodiment, the distance between the original text and the reverse translation result is calculated when calculating the distance between the original text and the reverse translation result. At this time, the original text and the reverse translation result may be expanded synonymously. For example, a synonym expansion unit 161 and a synonym dictionary 162 may be further provided as in the reliability calculation device 10b illustrated in FIG. FIG. 3 is a block diagram illustrating another configuration example of the reliability calculation apparatus according to the present embodiment.
同義語辞書162は、発音や表記は異なるが同じ意味をもつ単語または単語列を対応づけて記憶する。同義語展開部161は、原文または逆翻訳結果の各単語または単語列を、同義語辞書162を用いて複数の異なる表現に展開する。
The synonym dictionary 162 stores words or word strings that have the same meaning but different pronunciations and notations. The synonym expansion unit 161 expands each word or word string of the original text or the reverse translation result into a plurality of different expressions using the synonym dictionary 162.
そのような場合には、翻訳信頼度計算部15は、同義語展開部161によって同義語展開された複数の候補に対して距離を計算し、最も距離が近かった候補との距離を最終的な翻訳信頼度として選択してもよい。このような構成とすることで、例えばある単語が逆翻訳の結果、意味は同じであるが表記が異なる同義異表記語になった場合でも、意味が同じであれば距離は近いものと判断でき、不当に距離が大きくなることを防いでより適切な信頼度計算が可能となる。
In such a case, the translation reliability calculation unit 15 calculates distances for a plurality of candidates that have been synonymously expanded by the synonym expansion unit 161, and finally calculates the distance from the closest candidate. You may select as translation reliability. By adopting such a configuration, for example, even if a word has the same meaning but has the same meaning but different notation as a result of reverse translation, it can be determined that the distance is close if the meaning is the same. Therefore, it is possible to more appropriately calculate the reliability by preventing the distance from being unduly increased.
また、例えば、図4に示すように、さらに信頼度提示部17を備えて、当該信頼度算出装置10の信頼度提出部17で、逆翻訳部14で得られる逆翻訳結果と、翻訳信頼度計算部15で得られた信頼度とをあわせて提示するようにしてもよい。なお、図4は、本実施形態の信頼度算出装置の他の構成例を示すブロック図である。
Further, for example, as shown in FIG. 4, a reliability presentation unit 17 is further provided, and the reverse translation result obtained by the reverse translation unit 14 and the translation reliability obtained by the reliability submission unit 17 of the reliability calculation device 10. The reliability obtained by the calculation unit 15 may be presented together. FIG. 4 is a block diagram illustrating another configuration example of the reliability calculation apparatus according to the present embodiment.
以上のように、本実施形態によれば、原文と、翻訳処理結果である訳文を再度原文の言語に逆翻訳した逆翻訳結果との距離を翻訳信頼度として算出するので、翻訳処理として文法規則型翻訳など統計的機械翻訳以外の翻訳手法を用いても適切に信頼度を算出することができる。このように、適切な信頼度を得ることで、結果としてコミュニケーションの破綻を低減することが可能となる。
As described above, according to the present embodiment, the distance between the original sentence and the reverse translation result obtained by reversely translating the translated sentence that is the translation processing result into the original language is calculated as the translation reliability. The reliability can be appropriately calculated even by using a translation method other than statistical machine translation such as type translation. Thus, by obtaining an appropriate degree of reliability, it is possible to reduce communication failures as a result.
また、翻訳信頼度とともに逆翻訳結果を出力することで、例えば、出力先において低信頼度であった場合にユーザにその旨と逆翻訳結果を合わせて提示することで、原文を入力したユーザが翻訳対象とした第二の言語を理解できない場合であっても、話し手の言語による結果の確認が可能となり、その結果低信頼度となった原因やその箇所を推定させ、その部分の言い直しや言い換えを行わせることができる。
Also, by outputting the reverse translation result together with the translation reliability, for example, when the output destination is low reliability, the user who has input the original text can present the result together with the reverse translation result to the user. Even if you can't understand the second language you want to translate, you can check the result in the speaker's language, and as a result, you can estimate the cause and location of the low reliability, Paraphrasing can be performed.
次に、より具体的な例を用いて本実施形態を説明する。以下では、本発明による信頼度算出装置の第1の実施例として、図5に示す機械翻訳装置100の例を用いて説明する。図5に示す機械翻訳装置100は、入力部11と、信頼度算出部10と、結果判定部110と、出力部12とを備えている。
Next, this embodiment will be described using a more specific example. Hereinafter, a first embodiment of the reliability calculation apparatus according to the present invention will be described using the example of the machine translation apparatus 100 shown in FIG. The machine translation apparatus 100 illustrated in FIG. 5 includes an input unit 11, a reliability calculation unit 10, a result determination unit 110, and an output unit 12.
機械翻訳装置100は、例えば、CPU、RAM、ROMおよび不揮発性記憶装置を備える汎用的なコンピュータシステムにより実現される。すなわち、CPUが信頼度算出部10や結果判定部110の動作をプログラム言語により記述した機械翻訳プログラムを読み込み、読み込んだプログラムに従い機械翻訳処理を実行するよう構成されていてもよい。なお、機械翻訳装置100は、1台のコンピュータシステムである必要はなく、複数台のコンピュータシステムで構成されていてもよい。そのような構成において、機械翻訳装置100は、例えば、一つの翻訳エンジンとして動作し、低信頼度の結果を棄却することで結果として精度の高い翻訳結果を提供する。
The machine translation apparatus 100 is realized by a general-purpose computer system including a CPU, a RAM, a ROM, and a nonvolatile storage device, for example. That is, the CPU may be configured to read a machine translation program in which the operations of the reliability calculation unit 10 and the result determination unit 110 are described in a program language, and execute machine translation processing according to the read program. The machine translation apparatus 100 does not have to be a single computer system, and may be configured by a plurality of computer systems. In such a configuration, the machine translation apparatus 100 operates as, for example, one translation engine, and provides a highly accurate translation result as a result by rejecting a low-reliability result.
入力部11は、本装置に対して入力される第一の言語のテキストを受け付け、信頼度算出部10に出力する。入力部11は、例えば、テキスト入力デバイスとしてのキーボードでもよい。
The input unit 11 receives the text of the first language input to the apparatus and outputs it to the reliability calculation unit 10. The input unit 11 may be a keyboard as a text input device, for example.
信頼度算出部10は、入力部11からのテキスト入力を受け付け、翻訳処理と信頼度算出処理とを行う。信頼度算出部10は、図1の信頼度算出装置10に相当するものである。そのため、以下では図1と異なる動作についてのみ説明し、図1の構成と同じ動作については説明を省略する。なお、本例の信頼度算出部10は、図3の信頼度算出装置10bや図4の信頼度算出装置10cに相当するものであってもよい。
The reliability calculation unit 10 receives a text input from the input unit 11 and performs a translation process and a reliability calculation process. The reliability calculation unit 10 corresponds to the reliability calculation device 10 of FIG. Therefore, only the operation different from that in FIG. 1 will be described below, and the description of the same operation as the configuration in FIG. 1 will be omitted. The reliability calculation unit 10 in this example may correspond to the reliability calculation device 10b in FIG. 3 or the reliability calculation device 10c in FIG.
機械翻訳部13は、第一の言語を翻訳して第二の言語とした文すなわち訳文を、逆翻訳部14に出力するだけではなく、結果判定部110にも出力する。翻訳信頼度計算部15は、計算した信頼度を結果判定部110に出力する。
The machine translation unit 13 not only outputs to the reverse translation unit 14 a sentence that has been translated from the first language into the second language, that is, the translation, and also outputs it to the result determination unit 110. The translation reliability calculation unit 15 outputs the calculated reliability to the result determination unit 110.
結果判定部110は、機械翻訳部13から入力される翻訳結果の訳文を出力すべきかどうかを、翻訳信頼度計算部15から入力される信頼度に応じて判定する。例えば、入力された信頼度が予め定められた閾値以上であれば翻訳結果を出力し、そうでない場合は低信頼度であると判定して翻訳結果を出力せずに棄却する。
The result determination unit 110 determines whether or not the translation of the translation result input from the machine translation unit 13 should be output according to the reliability input from the translation reliability calculation unit 15. For example, if the input reliability is greater than or equal to a predetermined threshold value, the translation result is output, and if not, it is determined that the reliability is low and the result is rejected without outputting the translation result.
出力部12は、結果判定部110から得られる翻訳結果である訳文を出力する。例えば、訳文すなわち第二言語で表記されたテキストを画面表示してもよいし、同テキストを音声出力するための音声合成装置を組み込んだスピーカを用いて音声にして読み上げてもよい。また、出力部12は、結果判定部110が翻訳結果を棄却した場合には、何も出力しなくてもよいし、棄却された旨を示すメッセージとともに逆翻訳結果と信頼度とを出力してもよい。
The output unit 12 outputs a translation that is a translation result obtained from the result determination unit 110. For example, the translated text, that is, the text written in the second language may be displayed on the screen, or may be read out as a voice using a speaker incorporating a voice synthesizer for outputting the text. Moreover, the output part 12 does not need to output anything when the result determination part 110 rejects a translation result, and outputs a reverse translation result and reliability with the message which shows that it rejected. Also good.
なお、図5に示す例では、信頼度算出部10が機械翻訳部13を備える例を示したが、機械翻訳装置100が備えている既存の機械翻訳部(検索エンジン等)を利用する構成とすることも可能である。そのような場合には、逆翻訳部14は、機械翻訳装置100が備える翻訳エンジン等を利用して逆翻訳を行ってもよい。
In the example illustrated in FIG. 5, the reliability calculation unit 10 includes the machine translation unit 13, but the configuration uses an existing machine translation unit (such as a search engine) included in the machine translation apparatus 100. It is also possible to do. In such a case, the reverse translation unit 14 may perform reverse translation using a translation engine provided in the machine translation apparatus 100.
次に、本実施例にかかる翻訳処理の全体の流れを図6に示すフローチャートを参照して説明する。図6は、本発明の第1の実施例における翻訳処理の処理フローの一例を示すフローチャートである。図6に示すように、まず、機械翻訳装置100は、第一の言語のテキストを入力する(ステップS200)。具体的には、機械翻訳装置100は、入力部11を介して入力される第一の言語のテキストを受け付け、信頼度算出部10に出力する。
Next, the overall flow of the translation processing according to this embodiment will be described with reference to the flowchart shown in FIG. FIG. 6 is a flowchart showing an example of the processing flow of translation processing in the first embodiment of the present invention. As shown in FIG. 6, first, the machine translation apparatus 100 inputs text in a first language (step S200). Specifically, the machine translation apparatus 100 accepts text in the first language input via the input unit 11 and outputs the text to the reliability calculation unit 10.
次に、機械翻訳装置100は、入力されたテキストを翻訳する(ステップS201)。具体的には、機械翻訳装置100は、入力部11を介してユーザから入力された第一の言語のテキストに対し、機械翻訳部13で第二の言語への翻訳処理を行う。当該翻訳結果は、逆翻訳部14と結果判定部110に出力される。
Next, the machine translation device 100 translates the input text (step S201). Specifically, the machine translation device 100 performs translation processing into the second language by the machine translation unit 13 on the text of the first language input from the user via the input unit 11. The translation result is output to the reverse translation unit 14 and the result determination unit 110.
次に、機械翻訳装置100は、逆翻訳を行う(ステップS202)。具体的には、機械翻訳装置100は、機械翻訳部13にて得られた翻訳結果に対して、逆翻訳部14で再び第一の言語へ逆翻訳処理を行う。
Next, the machine translation apparatus 100 performs reverse translation (step S202). Specifically, the machine translation apparatus 100 performs reverse translation processing on the translation result obtained by the machine translation unit 13 to the first language again by the reverse translation unit 14.
次に、機械翻訳装置100は、信頼度を計算する(ステップS203)。具体的には、機械翻訳装置100の翻訳信頼度計算部15において、入力部11を介して入力された翻訳前の第一の言語で記述された原文と、逆翻訳部14にて再び第一の言語へ翻訳された逆翻訳結果とを入力とし、両者の距離を計算して信頼度とする。
Next, the machine translation device 100 calculates the reliability (step S203). Specifically, in the translation reliability calculation unit 15 of the machine translation apparatus 100, the original text described in the first language before translation input via the input unit 11 and the first in the reverse translation unit 14 again. The reverse translation result translated into the language is input, and the distance between the two is calculated as the reliability.
図7は、本実施例における信頼度の算出例を示す説明図である。例えば、図7(a)に示すように、第一の言語である英語での入力文「what would you like to drink」に対し、第二の言語である日本語での翻訳結果が「何を飲みたいですか(nani wo nomitaidesuka)」であり、その逆翻訳結果が「What would you like to drink? 」であったとする。このとき、逆翻訳結果は入力文を完全に再現しており、入力文と逆翻訳結果の信頼度は、BLEUスコアを1-gramにおいて算出すると、1.0となる。
FIG. 7 is an explanatory diagram showing an example of calculation of reliability in this embodiment. For example, as shown in FIG. 7A, for the input sentence “what would you like to drink” in English as the first language, the translation result in Japanese as the second language is “What. Suppose you want to drink (nani wo nomitaidesuka) ”and the reverse translation result is“ What would you like to drink? ”. At this time, the reverse translation result completely reproduces the input sentence, and the reliability of the input sentence and the reverse translation result is 1.0 when the BLEU score is calculated in 1-gram.
一方、図7(b)の例を参照すると、第一の言語である英語での入力文「do you have chairs for children 」に対し、第二の言語である中国語への翻訳結果が図中のとおりであり、その逆翻訳結果が「Is there a lecture of a child?」であったとする。ここでは誤翻訳が発生しており、同様に信頼度を算出すると、0.0となる。
On the other hand, referring to the example of FIG. 7 (b), the result of translation into Chinese, the second language, for the input sentence “do you have chairs for children” in the first language is shown in the figure. And the reverse translation result is “Is there a lecture of a child?”. Here, mistranslation has occurred, and when the reliability is calculated in the same manner, it becomes 0.0.
なお、このとき、図3の構成で示したように原文または逆翻訳結果の各単語または単語列を、同義語辞書162を用いて同義語展開部161が複数の候補に展開してもよい。そのような場合に、翻訳信頼度計算部15は、同義語展開された複数の候補のそれぞれの組み合わせに対して距離を計算し、最も距離の近いものを最終的な翻訳信頼度として選択してもよい。例えば、図7(b)の原文側において、「chairs」を「sofas」「stools」などに変換したり、「do you have」を「are there」などに変換して原文を複数の候補に展開してもよい。同様に、逆翻訳結果においても「lecture」を「class」などに変換して複数の候補に展開してもよい。そのようにして展開された複数の候補のすべての組み合わせについて距離を計算し、最も距離の近いものを信頼度として選択すればよい。なお、複数候補への展開はいずれか一方でもよい。同義語展開を行うことで、逆翻訳時に意味は同じだが表記が変わってしまったような場合でも精度の高い信頼度を計算することができる。
At this time, as shown in the configuration of FIG. 3, the synonym expansion unit 161 may expand each word or word string of the original text or the reverse translation result into a plurality of candidates using the synonym dictionary 162. In such a case, the translation reliability calculation unit 15 calculates the distance for each combination of a plurality of synonym expanded candidates, and selects the closest one as the final translation reliability. Also good. For example, on the source side of Fig. 7 (b), "chairs" is converted to "sofas", "stools", etc., or "do you have" is converted to "are there", etc. May be. Similarly, in the reverse translation result, “lecture” may be converted into “class” or the like and expanded into a plurality of candidates. The distances may be calculated for all combinations of the plurality of candidates developed in this manner, and the closest one may be selected as the reliability. In addition, the expansion to a plurality of candidates may be any one. By performing synonym expansion, it is possible to calculate highly reliable reliability even when the meaning is the same at the time of reverse translation but the notation has changed.
次に、機械翻訳装置100は、結果判定を行う(ステップS204)。具体的には、機械翻訳装置100は、結果判定部110において、機械翻訳部13から通知された翻訳結果の訳文を出力すべきかどうかを、翻訳信頼度計算部15から通知される信頼度に応じて判定する。例えば、図7(a)の場合、信頼度が1.0と高いため、受理すなわち出力可と判定する。また、図7(b)の場合、信頼度が0.0と低いため、棄却すなわち出力不可とする。
Next, the machine translation apparatus 100 performs a result determination (step S204). Specifically, the machine translation apparatus 100 determines whether the result determination unit 110 should output the translation of the translation result notified from the machine translation unit 13 according to the reliability notified from the translation reliability calculation unit 15. Judgment. For example, in the case of FIG. 7A, since the reliability is as high as 1.0, it is determined that acceptance, that is, output is possible. Further, in the case of FIG. 7B, since the reliability is as low as 0.0, rejection, that is, output is impossible.
次に、機械翻訳装置100は、結果を出力する(ステップS205)。具体的には、機械翻訳装置100は、結果判定部110での判定の結果得られた翻訳結果を、出力部12を介して出力することで例えばディスプレイ等に表示する。
Next, the machine translation apparatus 100 outputs the result (step S205). Specifically, the machine translation apparatus 100 outputs the translation result obtained as a result of the determination by the result determination unit 110 via the output unit 12 and displays the result on a display, for example.
このように、低信頼度の結果を棄却することで結果として精度の高い翻訳を実現することができる。なお、いずれの場合も翻訳結果は出力し、同時に信頼度を表示するようにしてもよい。また、図4の構成で示したように低信頼度で棄却された場合は、逆翻訳結果を信頼度と併せて表示し、ユーザに再入力を促してもよい。
Thus, by rejecting results with low reliability, translation with high accuracy can be realized as a result. In any case, the translation result may be output and the reliability may be displayed at the same time. Moreover, when rejected with low reliability as shown in the configuration of FIG. 4, the reverse translation result may be displayed together with the reliability to prompt the user to input again.
なお、信頼度の計算を単語または単語列単位で求めた場合は、例えば、図7(c)、(d)のようにして信頼度を提示してもよい。例えば図7(c)に示すように、第一の言語である英語での入力文「what would you like to drink」に対し、第二の言語である日本語での翻訳結果が「何を飲みたいですか(nani wo nomitaidesuka)」であり、その逆翻訳結果が「What would you like to drink?」であったとする。このとき、逆翻訳結果は入力文を完全に再現しているため、すべての単語について信頼度は1.0となる。一方、図7(d)の例を参照すると、第一の言語である英語での入力文「which will you take 」に対し、第二の言語である日本語での翻訳結果が「あなたはどちらがかかりますか(anata ha dochira ga kakarimasuka)」であり、その逆翻訳結果が「Which is your take? 」であったとする。ここでは誤翻訳が発生しているが、逆翻訳により再現された単語については信頼度を高く表示することで、それを見たユーザが、再現されなかった低信頼度部分を言い換えるといったことが容易になる。
When the calculation of the reliability is obtained in units of words or word strings, the reliability may be presented as shown in FIGS. 7C and 7D, for example. For example, as shown in FIG. 7C, for the input sentence “what would you like to drink” in English as the first language, the translation result in Japanese as the second language is Suppose you want to (nani wo nomitaidesuka) ”and the reverse translation result is“ What 」wouldnyou like to drink?”. At this time, since the reverse translation result completely reproduces the input sentence, the reliability is 1.0 for all words. On the other hand, referring to the example of FIG. 7 (d), the translation result in Japanese, which is the second language, for the input sentence “which will you take”, which is the first language, is “Who are you? "Do you take (anata ha dochira ga kakarimasuka)" and the reverse translation result is "Which is your take?". Here, mistranslation occurs, but it is easy for the user who sees the word reproduced by reverse translation to rephrase the low reliability part that was not reproduced by displaying it with high reliability. become.
なお、図7(c)および図7(d)の例では、簡単のため表層が一致している1-gramでは信頼度を1.0に、不一致の場合には0.0としているが、信頼度の値としてはこれに限らない。例えば、表層だけでなく品詞や読み情報などとの組み合わせ、活用等の違いを考慮するといったことも可能である。例えば、表層のみ一致している場合には0.8、品詞も一致していれば0.9などとしてもよいし、活用等の違い(図7(d)の例ではyou とyour)だけであれば0.3といったスコア付けも可能である。
In the examples of FIGS. 7C and 7D, for simplicity, the reliability is set to 1.0 for 1-gram where the surface layers match, and 0.0 for non-matching, The reliability value is not limited to this. For example, it is possible to consider not only the surface layer but also the combination with the part of speech and the reading information, the difference in utilization, and the like. For example, 0.8 may be used if only the surface layer is matched, 0.9 may be used if the parts of speech are also matched, and only the difference in utilization (you and your in the example of FIG. 7D). If so, a score of 0.3 is also possible.
実施形態2.
次に、本発明の第2の実施形態について説明する。本実施形態では、音声認識などテキスト以外の入力を想定し、かつその信頼度との統合を行うことで、より適切な信頼度を算出する。図8は、本発明の第2の実施形態の信頼度算出装置の構成例を示すブロック図である。図8に示す信頼度算出装置10dは、音声認識結果の単語または単語列とその信頼度を入力とし、音声認識結果の信頼度と翻訳結果の信頼度とを統合した信頼度を出力する。 Embodiment 2. FIG.
Next, a second embodiment of the present invention will be described. In the present embodiment, more appropriate reliability is calculated by assuming input other than text, such as voice recognition, and integrating the reliability. FIG. 8 is a block diagram illustrating a configuration example of the reliability calculation apparatus according to the second embodiment of this invention. Thereliability calculation device 10d illustrated in FIG. 8 receives the word or word string of the speech recognition result and the reliability thereof, and outputs a reliability obtained by integrating the reliability of the speech recognition result and the reliability of the translation result.
次に、本発明の第2の実施形態について説明する。本実施形態では、音声認識などテキスト以外の入力を想定し、かつその信頼度との統合を行うことで、より適切な信頼度を算出する。図8は、本発明の第2の実施形態の信頼度算出装置の構成例を示すブロック図である。図8に示す信頼度算出装置10dは、音声認識結果の単語または単語列とその信頼度を入力とし、音声認識結果の信頼度と翻訳結果の信頼度とを統合した信頼度を出力する。 Embodiment 2. FIG.
Next, a second embodiment of the present invention will be described. In the present embodiment, more appropriate reliability is calculated by assuming input other than text, such as voice recognition, and integrating the reliability. FIG. 8 is a block diagram illustrating a configuration example of the reliability calculation apparatus according to the second embodiment of this invention. The
図8に示す信頼度算出装置10dは、機械翻訳部13と、逆翻訳部14と、翻訳信頼度計算部15と、信頼度統合部21とを備える。また、信頼度算出装置10dは、この他に直接または間接的に、音声認識結果入力部210と、出力部12とを備えていてもよい。ここで、機械翻訳部13と逆翻訳部14と翻訳信頼度計算部15とは、図1に示す第1の実施形態と同様であるため、説明を省略する。以下では、第1の実施形態と異なる部分についてのみ説明する。
8 includes a machine translation unit 13, a reverse translation unit 14, a translation reliability calculation unit 15, and a reliability integration unit 21. The reliability calculation device 10d illustrated in FIG. In addition, the reliability calculation device 10d may include a speech recognition result input unit 210 and an output unit 12 directly or indirectly. Here, the machine translation unit 13, the reverse translation unit 14, and the translation reliability calculation unit 15 are the same as those in the first embodiment shown in FIG. Below, only a different part from 1st Embodiment is demonstrated.
音声認識結果入力部210は、音声で入力された翻訳対象の文または文章に対する音声認識結果と、その信頼度とを入力する。
The speech recognition result input unit 210 inputs a speech recognition result for a sentence or sentence to be translated input by speech and its reliability.
機械翻訳部13と翻訳信頼度計算部15とは、音声認識結果入力部210から音声認識結果を、原文テキストとして受け取る。
The machine translation unit 13 and the translation reliability calculation unit 15 receive the speech recognition result from the speech recognition result input unit 210 as the original text.
信頼度統合部21は、音声認識結果入力部210から音声認識結果に対する信頼度である音声認識信頼度を入力し、さらに翻訳信頼度計算部15から翻訳信頼度を入力し、入力された音声認識信頼度と翻訳信頼度とを統合する。信頼度統合部21は、音声認識信頼度と翻訳信頼度を、例えば線形補間により統合して統合信頼度としてもよい。
The reliability integration unit 21 inputs the speech recognition reliability, which is the reliability of the speech recognition result, from the speech recognition result input unit 210, and further inputs the translation reliability from the translation reliability calculation unit 15. Integrate reliability and translation reliability. The reliability integration unit 21 may integrate the speech recognition reliability and the translation reliability by linear interpolation, for example, to obtain an integrated reliability.
例えば、統合信頼度をCM、音声認識信頼度をCMASR、翻訳信頼度をCMMTとおくと、統合信頼度CMは、線形補間係数αを用いて以下の式(4)のように表される。
For example, if the integrated reliability is CM, the speech recognition reliability is CM ASR , and the translation reliability is CM MT , the integrated reliability CM is expressed by the following equation (4) using the linear interpolation coefficient α. The
CM=(1-α)×CMASR+α×CMMT ・・・式(4)
CM = (1−α) × CM ASR + α × CM MT Formula (4)
音声認識信頼度CMASRとしては、例えば音声認識装置が単語単位に計算する単語事後確率(Word Posteriori Probability )を用いる方法が挙げられる。なお、音声認識信頼度の付与方法はこれに限らない。単語事後確率を計算する方法は、公知技術として良く知られているものであるから、ここでは詳細な説明を省略する。
As the speech recognition reliability CM ASR , for example, there is a method using a word posteriori probability (Word Posteriori Probability) calculated by the speech recognition device for each word. Note that the method of providing the voice recognition reliability is not limited to this. Since the method for calculating the word posterior probability is well known as a known technique, a detailed description thereof is omitted here.
ところで、一般に、翻訳信頼度CMMTが文単位で付与されるのに対して、音声認識信頼度CMASRは単語事後確率のように単語単位で付与されることが多い。このような場合には、音声認識信頼度CMASRを文単位に拡張して用いてもよい。音声認識信頼度CMASRを文単位に拡張する方法としては、得られる単語事後確率を文全体で正規化してもよいし、文全体の事後確率を各単語事後確率の同時確率と捉えてもよい。
By the way, in general, the translation reliability CM MT is given in sentence units, whereas the speech recognition reliability CM ASR is often given in word units like word posterior probabilities. In such a case, the speech recognition reliability CM ASR may be extended in sentence units. As a method of extending the speech recognition reliability CM ASR in sentence units, the obtained word posterior probabilities may be normalized for the entire sentence, or the posterior probabilities for the entire sentence may be regarded as the joint probabilities for each word posterior probability. .
以下の式(5)は、文{wn
l}を構成する各単語wiの事後確率をP(wi|X)としたとき、単語事後確率を文全体で正規化して音声認識信頼度CMASRを文単位に拡張する場合の計算例である。
The following equation (5) is obtained by normalizing the word posterior probabilities for the entire sentence, where P (w i | X) is the posterior probability of each word w i constituting the sentence {w n l }, and the speech recognition reliability. It is a calculation example in the case of extending CM ASR in sentence units.
また、以下の式(6)は、文全体の事後確率を各単語事後確率の同時確率と捉えて音声認識信頼度CMASRを文単位に拡張する場合の計算例である。
Further, the following formula (6) is a calculation example in the case where the posterior probability of the whole sentence is regarded as the simultaneous probability of each word posterior probability and the speech recognition reliability CM ASR is expanded in sentence units.
逆に、機械翻訳信頼度CMMTを、単語または単語列単位にするには、共有N-gramと音声認識のN-gram言語モデルまたは音声認識信頼度CMASRとを単語または単語列単位で組み合わせることで実現可能である。例えば、簡単には、共有N-gramでない単語すなわち逆翻訳で再現しなかった単語については、音声認識信頼度CMASRに一定のペナルティ値を加えて統合信頼度CMを単語単位で求め、その後、文全体で正規化するとよい。このように単語単位に統合信頼度を求めることで、一文内での低信頼度区間の提示といったことが可能になる。
Conversely, in order to set the machine translation reliability CM MT in units of words or word strings, the shared N-gram and the speech recognition N-gram language model or the voice recognition reliability CM ASR are combined in units of words or word strings. This is possible. For example, for a word that is not a shared N-gram, that is, a word that has not been reproduced by reverse translation, a certain penalty value is added to the speech recognition reliability CM ASR to obtain an integrated reliability CM in units of words. Normalize the whole sentence. Thus, by obtaining the integrated reliability in units of words, it becomes possible to present a low reliability section within a sentence.
出力部12は、信頼度算出装置10dから出力される信頼度(ここでは、統合信頼度)をユーザに表示するディスプレイ等である。出力部12は、翻訳結果とともにその文単位や単語単位に求められた信頼度を表示してもよい。なお、本実施形態の場合、提示する信頼度としては、翻訳信頼度や入力部に音声認識など他のモジュールを想定する場合にその認識結果に対する信頼度(音声認識信頼度等)を用いてもよい。なお、これらを統合信頼度として組み合わせて用いてもよい。
The output unit 12 is a display or the like that displays the reliability (here, integrated reliability) output from the reliability calculation device 10d to the user. The output unit 12 may display the reliability obtained for each sentence or each word along with the translation result. In the case of this embodiment, as the reliability to be presented, the reliability of the recognition result (speech recognition reliability, etc.) may be used when assuming other modules such as translation reliability and speech recognition in the input unit. Good. These may be used in combination as the integrated reliability.
なお、本実施の形態では原文テキストとして音声認識結果を入力することを想定しているが、前段に置く構成としては音声認識に限らない。例えば、OCR(Optical Character Reader:文字読取装置)やタッチパネルを用いた文字入力結果(または文字認識結果)とその信頼度とを入力としても同様の構成が可能である。
In this embodiment, it is assumed that the speech recognition result is input as the original text, but the configuration placed in the previous stage is not limited to speech recognition. For example, a similar configuration is possible by inputting a character input result (or character recognition result) using an OCR (Optical Character Reader) or a touch panel and its reliability.
また、本実施形態においても、第1の実施形態と同様に、同義語展開部161および同義語辞書162を備えて同義語展開を行うことで、より適切な信頼度計算を行うことができる。このとき、音声認識に用いる音声認識辞書と、機械翻訳に用いる翻訳辞書とが共通に保有する単語または単語列のみを対象として同義語展開を行うことで、より効率を高めることができる。すなわち、未知な単語への無駄な展開を防ぎ、翻訳可能な範囲でのみ同義語展開することで、処理量を減らすことができる。
Also in the present embodiment, as in the first embodiment, the synonym expansion unit 161 and the synonym dictionary 162 are provided and synonym expansion is performed, so that more appropriate reliability calculation can be performed. At this time, it is possible to further increase efficiency by performing synonym expansion only on words or word strings that are commonly held by the speech recognition dictionary used for speech recognition and the translation dictionary used for machine translation. That is, it is possible to reduce the amount of processing by preventing useless expansion to unknown words and expanding synonyms only within a translatable range.
また、例えば、図10に示す信頼度算出装置10eのように、さらに信頼度提示部17を備えて、信頼度提出部17で逆翻訳部14で得られる逆翻訳結果と、信頼度統合部21で得られた信頼度とをあわせて提示するようにしてもよい。なお、図10は、本実施形態の信頼度算出装置の他の構成例を示すブロック図である。なお、信頼度提示部17にて提示する信頼度は、文(または発話全体)単位である必要はなく、例えば単語単位に提示してもよい。
Further, for example, as in the reliability calculation device 10e shown in FIG. 10, the reliability presentation unit 17 is further provided, the reverse translation result obtained by the reverse translation unit 14 in the reliability submission unit 17, and the reliability integration unit 21. You may make it show together with the reliability obtained by. FIG. 10 is a block diagram illustrating another configuration example of the reliability calculation apparatus according to the present embodiment. The reliability presented by the reliability presentation unit 17 does not need to be in units of sentences (or the entire utterance), and may be presented in units of words, for example.
次に、本実施形態の動作について説明する。以下では、本実施形態の信頼度算出装置10dにおける信頼度算出処理について図9を参照して説明する。図9は、本実施形態の信頼度算出装置10dにおける信頼度算出処理の処理フローの一例を示すフローチャートである。図9に示すように、まず信頼度算出装置10dは、翻訳対象の原文となる音声認識結果とその信頼度とを入力する(ステップS300)。ここでは、音声認識結果入力部210を介して、音声認識結果の入力を、第一の言語で記述された文すなわち原文として受け付け、受け付けた原文を機械翻訳部13および翻訳信頼度計算部15に出力する。同時に、その音声認識結果の音声認識信頼度の入力を受け付け、受け付けた音声認識信頼度を信頼度統合部21に出力する。
Next, the operation of this embodiment will be described. Below, the reliability calculation process in the reliability calculation apparatus 10d of this embodiment is demonstrated with reference to FIG. FIG. 9 is a flowchart illustrating an example of a processing flow of reliability calculation processing in the reliability calculation device 10d of the present embodiment. As shown in FIG. 9, first, the reliability calculation device 10d inputs a speech recognition result as an original sentence to be translated and its reliability (step S300). Here, the input of the speech recognition result is accepted as a sentence written in the first language, that is, the original text via the speech recognition result input section 210, and the received original text is sent to the machine translation section 13 and the translation reliability calculation section 15. Output. At the same time, an input of the voice recognition reliability of the voice recognition result is received, and the received voice recognition reliability is output to the reliability integration unit 21.
次に、機械翻訳部13が、入力された原文を翻訳する(ステップS301)。機械翻訳部13は、入力された原文に対して、原文の言語である第一の言語から指定された他の言語である第二の言語への翻訳処理を実行し、その翻訳結果を逆翻訳部14に出力する。
Next, the machine translation unit 13 translates the input original text (step S301). The machine translation unit 13 performs a translation process on the input original sentence from the first language that is the original language to the second language that is the other language specified, and reversely translates the translation result To the unit 14.
次に、逆翻訳部14が、機械翻訳部13の翻訳結果である訳文に対して、逆翻訳を行う(ステップS302)。逆翻訳部14は、機械翻訳部13から入力された翻訳結果である訳文に対して、訳文の言語である第二の言語から再び原文の言語である第一の言語への翻訳処理を実行し、その翻訳結果である逆翻訳結果を翻訳信頼度計算部15に出力する。
Next, the reverse translation unit 14 performs reverse translation on the translation that is the translation result of the machine translation unit 13 (step S302). The reverse translation unit 14 executes a translation process from the second language, which is the translated language, to the first language, which is the original language, again on the translation that is the translation result input from the machine translation unit 13. The reverse translation result, which is the translation result, is output to the translation reliability calculation unit 15.
次に、翻訳信頼度計算部15が、信頼度を計算する(ステップS303)。翻訳信頼度計算部15は、音声結果入力部210を介して入力された翻訳前の第一の言語で記述された原文と、逆翻訳部14にて再び第一の言語に翻訳された逆翻訳結果とを入力とし、両者の距離を計算して翻訳信頼度とする。なお、本実施形態では、ここで算出される翻訳信頼度を、単純に翻訳処理結果に対する信頼度として扱う。
Next, the translation reliability calculation unit 15 calculates the reliability (step S303). The translation reliability calculation unit 15 uses the original text described in the first language before translation input via the speech result input unit 210 and the reverse translation translated into the first language again by the reverse translation unit 14. The result is input, and the distance between the two is calculated as the translation reliability. In the present embodiment, the translation reliability calculated here is simply handled as the reliability for the translation processing result.
次に、信頼度統合部21が、原文の認識処理に対する信頼度である音声認識信頼度と、翻訳信頼度とを統合する(ステップS304)。信頼度統合部21は、音声認識結果入力部210から入力された音声認識信頼度と、翻訳信頼度計算部15から入力された翻訳信頼度とを、例えば線形補間により統合する。なお、統合する信頼度は、文単位である場合や単語または単語列単位である場合がある。
Next, the reliability integration unit 21 integrates the speech recognition reliability, which is the reliability of the original text recognition process, and the translation reliability (step S304). The reliability integration unit 21 integrates the speech recognition reliability input from the speech recognition result input unit 210 and the translation reliability input from the translation reliability calculation unit 15 by, for example, linear interpolation. Note that the reliability to be integrated may be a sentence unit or a word or a word string unit.
最後に、信頼度算出装置10dは、結果を出力する(ステップS305)。信頼度算出装置10dは、信頼度統合部21によって得られた統合信頼度を、例えば、ディスプレイ等の出力部12を介して出力してユーザに表示する。このとき、信頼度算出装置10dは、統合信頼度とともに逆翻訳結果を出力してもよい。また、統合信頼度とともにその統合信頼度の算出に用いた音声認識信頼度と翻訳結果信頼度とを付加情報として出力してもよい。
Finally, the reliability calculation device 10d outputs the result (step S305). The reliability calculation device 10d outputs the integrated reliability obtained by the reliability integration unit 21 via the output unit 12 such as a display and displays it to the user. At this time, the reliability calculation apparatus 10d may output the reverse translation result together with the integrated reliability. In addition to the integrated reliability, the speech recognition reliability and the translation result reliability used to calculate the integrated reliability may be output as additional information.
以上のように、本実施形態によれば、音声認識などテキスト以外の入力が行われる場合に、入力された原文に対する第一の言語による認識処理の信頼度との統合を行うことで、より適切な信頼度を算出することができる。
As described above, according to the present embodiment, when input other than text, such as speech recognition, is performed, integration with the reliability of recognition processing in the first language for the input original sentence is more appropriate. Reliable reliability can be calculated.
また、低信頼度であった場合に、逆翻訳結果と信頼度とをあわせて提示することで、原文を入力したユーザが翻訳対象とした第二の言語を理解できない場合であっても、話し手の言語による結果の確認が可能となり、その結果低信頼度となった原因やその箇所を推定させ、その部分の言い直しや言い換えを行わせることができる。さらに、本実施形態では、単語単位での信頼度を付与することができるため、低信頼度となった単語に対応する逆翻訳分の文章表現を強調して提示することにより、話し手の言語による結果の確認がより容易に可能となり、その結果低信頼度となった原因やその箇所の推定をさらに容易にさせ、その部分の言い直しや言い換えを行わせることができる。
In addition, if the reliability is low, presenting the reverse translation result and reliability together, even if the user who entered the original text cannot understand the second language to be translated, As a result, it is possible to check the result and to estimate the cause and location of the low reliability, and to rephrase or rephrase the portion. Furthermore, in the present embodiment, since reliability can be given in units of words, by emphasizing and presenting a sentence expression for the reverse translation corresponding to the word that has become low reliability, The result can be confirmed more easily, and as a result, the cause of the low reliability and the location can be estimated more easily, and the portion can be rephrased and rephrased.
次に、より具体的な例を用いて本実施形態を説明する。以下では、本発明による信頼度算出装置の第2の実施例として、図11に示す音声翻訳システム200の例を説明する。図10に示す音声翻訳システム200は、音声入力部211と、音声認識部212と、信頼度算出部10dと、結果判定部220と、出力部12とを備える。
Next, this embodiment will be described using a more specific example. Hereinafter, an example of the speech translation system 200 shown in FIG. 11 will be described as a second embodiment of the reliability calculation apparatus according to the present invention. The speech translation system 200 illustrated in FIG. 10 includes a speech input unit 211, a speech recognition unit 212, a reliability calculation unit 10d, a result determination unit 220, and an output unit 12.
音声翻訳システム200は、例えば、CPU、RAM、ROMおよび不揮発性記憶装置を備える汎用的なコンピュータシステムにより実現される。すなわち、CPUが音声認識部212や信頼度算出部10d、結果判定部220の動作をプログラム言語により記述した音声翻訳プログラムを読み込み、読み込んだプログラムに従い音声翻訳処理を実行するよう構成されていてもよい。なお、音声翻訳システム200は、1台のコンピュータシステムである必要はなく、複数台のコンピュータシステムで構成されていてもよい。そのような構成において、音声翻訳システム200は、翻訳対象の原文となる第一の言語の音声を受け付け、その音声が表している文または文章を第二の言語に翻訳して、翻訳結果を信頼度とともに出力する。
The speech translation system 200 is realized by, for example, a general-purpose computer system that includes a CPU, a RAM, a ROM, and a nonvolatile storage device. That is, the CPU may be configured to read a speech translation program in which the operations of the speech recognition unit 212, the reliability calculation unit 10d, and the result determination unit 220 are described in a program language, and execute the speech translation process according to the read program. . Note that the speech translation system 200 does not have to be a single computer system, and may be configured by a plurality of computer systems. In such a configuration, the speech translation system 200 receives the speech of the first language that is the original sentence to be translated, translates the sentence or sentence represented by the speech into the second language, and trusts the translation result. Output with degrees.
音声入力部211は、本システムに対して入力される第一の言語の音声を受け付け、音声認識部211に出力する。例えば、入力デバイスとしてのマイクロフォンでもよい。
The voice input unit 211 receives the first language voice input to the system and outputs it to the voice recognition unit 211. For example, a microphone as an input device may be used.
音声認識部210は、音声入力部211を介して入力された音声を音声認識処理し、音声認識結果とその信頼度である音声認識信頼度を、信頼度算出部10dに出力する。
The voice recognition unit 210 performs voice recognition processing on the voice input via the voice input unit 211, and outputs a voice recognition result and a voice recognition reliability that is a reliability level to the reliability calculation unit 10d.
信頼度算出部10dは、音声認識部210からの音声認識結果とその信頼度の入力を翻訳対象とする原文と原文に対する信頼度として受け付け、翻訳処理と翻訳信頼度および統合信頼度の算出処理とを行う。信頼度算出部10dは、図8に示す信頼度算出装置10dに相当するものである。そのため、以下では、図8と異なる動作についてのみ説明し、図8の構成と同じ動作については説明を省略する。なお、本例の信頼度算出部10dは、図10の信頼度算出装置10eに相当するものや、さらに図3に示すような同義語展開部161およぼ同義語辞書162を備える構成であってもよい。
The reliability calculation unit 10d accepts the speech recognition result from the speech recognition unit 210 and the input of the reliability as the original text to be translated and the reliability of the original text, and the translation process, the calculation process of the translation reliability and the integrated reliability, I do. The reliability calculation unit 10d corresponds to the reliability calculation device 10d shown in FIG. Therefore, only operations different from those in FIG. 8 will be described below, and description of the same operations as those in the configuration in FIG. 8 will be omitted. In addition, the reliability calculation unit 10d of this example has a configuration equivalent to the reliability calculation device 10e of FIG. 10, and further includes a synonym expansion unit 161 and a synonym dictionary 162 as shown in FIG. Also good.
機械翻訳部13は、第一の言語を翻訳して第二の言語とした文すなわち訳文を、逆翻訳部14に出力するだけではなく、結果判定部220にも出力する。信頼度統合部21は、統合した信頼度を結果判定部220に出力する。結果判定部220は、機械翻訳部13から入力される翻訳結果の訳文を出力すべきかどうかを、信頼度統合部21から入力される信頼度すなわち統合信頼度に応じて判定する。
The machine translation unit 13 translates the first language into the second language, that is, the translation, not only to the reverse translation unit 14 but also to the result determination unit 220. The reliability integration unit 21 outputs the integrated reliability to the result determination unit 220. The result determination unit 220 determines whether the translation of the translation result input from the machine translation unit 13 should be output according to the reliability input from the reliability integration unit 21, that is, the integrated reliability.
出力部12は、結果判定部220から得られる翻訳結果である訳文を出力する。例えば、訳文すなわち第二言語で表記されたテキストを画面表示してもよいし、同テキストを音声出力するための音声合成装置を組み込んだスピーカを用いて音声にて読み上げてもよい。また、出力部12は、結果判定部220が翻訳結果を棄却した場合には、何も出力しなくてもよいし、棄却された旨を示すメッセージとともに逆翻訳結果と信頼度とを出力してもよい。
The output unit 12 outputs a translation that is a translation result obtained from the result determination unit 220. For example, the translated text, that is, the text written in the second language may be displayed on the screen, or may be read out by voice using a speaker incorporating a voice synthesizer for outputting the text as voice. Further, the output unit 12 does not need to output anything when the result determination unit 220 rejects the translation result, and outputs the reverse translation result and the reliability together with a message indicating that the result is rejected. Also good.
次に、本実施例にかかる翻訳処理の全体の流れを図12に示すフローチャートを参照して説明する。図12は、本発明の第2の実施例における翻訳処理の処理フローの一例を示すフローチャートである。図12に示すように、まず、音声翻訳システム200は、第一の言語の音声を入力する(ステップS400)。具体的には、音声翻訳システム200は、音声入力部211を介して入力される第一の言語の音声を受け付け、音声認識部212に出力する。
Next, the overall flow of the translation processing according to this embodiment will be described with reference to the flowchart shown in FIG. FIG. 12 is a flowchart showing an example of a processing flow of translation processing in the second embodiment of the present invention. As shown in FIG. 12, first, the speech translation system 200 inputs speech in the first language (step S400). Specifically, the speech translation system 200 accepts the first language speech input via the speech input unit 211 and outputs it to the speech recognition unit 212.
次に、音声翻訳システム200は、入力された音声を音声認識する(ステップS401)。具体的には、音声翻訳システム200は、音声入力部211から入力された音声に対して音声認識部212が音声認識処理を実施し、音声認識結果とその信頼度である音声認識信頼度を求め、得られた音声認識結果と音声認識信頼度とを信頼度算出部10dに出力する。なお、音声を入力して音声認識結果としてのテキストを出力する音声認識処理の方法、およびその際に音声認識結果の信頼度を計算する方法については、公知技術として良く知られているものであるから、ここでは詳細な説明を省略する。音声信頼度算出部10dでは、少なくとも機械翻訳部13、翻訳信頼度計算部15に音声認識結果が出力され、また得られた音声認識結果が出力され、信頼度統合部21に音声認識結果が出力される。
Next, the speech translation system 200 recognizes the input speech (step S401). Specifically, in the speech translation system 200, the speech recognition unit 212 performs speech recognition processing on the speech input from the speech input unit 211, and obtains speech recognition results and speech recognition reliability that is reliability. The obtained voice recognition result and the voice recognition reliability are output to the reliability calculation unit 10d. Note that a speech recognition processing method for inputting speech and outputting text as a speech recognition result, and a method for calculating the reliability of the speech recognition result at that time are well known in the art. Therefore, detailed description is omitted here. In the speech reliability calculation unit 10d, the speech recognition result is output to at least the machine translation unit 13 and the translation reliability calculation unit 15, the obtained speech recognition result is output, and the speech recognition result is output to the reliability integration unit 21. Is done.
次に、音声翻訳システム200は、音声認識結果を翻訳する(ステップS402)。具体的には、音声翻訳システム200は、音声認識部212から入力された音声認識結果のテキストを機械翻訳部13によって翻訳し、その翻訳結果を逆翻訳部14と結果判定部220に出力する。
Next, the speech translation system 200 translates the speech recognition result (step S402). Specifically, the speech translation system 200 translates the text of the speech recognition result input from the speech recognition unit 212 by the machine translation unit 13, and outputs the translation result to the reverse translation unit 14 and the result determination unit 220.
次に、音声翻訳システム200は、逆翻訳を行う(ステップS403)。具体的には、音声翻訳システム200は、機械翻訳部13によって得られた翻訳結果に対して、逆翻訳部14で再び第一の言語に逆翻訳処理を行う。
Next, the speech translation system 200 performs reverse translation (step S403). Specifically, the speech translation system 200 performs reverse translation processing on the first language again by the reverse translation unit 14 on the translation result obtained by the machine translation unit 13.
次に、音声翻訳システム200は、翻訳信頼度を計算する(ステップS404)。具体的には、音声翻訳システム200の翻訳信頼度計算部15において、音声認識部212による音声認識結果である翻訳前の第一の言語で記述された原文と、逆翻訳部14にて再び第一の言語へ翻訳された逆翻訳結果とを入力とし、両者の距離を計算して翻訳信頼度とする。なお、ここで算出される翻訳信頼度は、翻訳処理に対する信頼度である。
Next, the speech translation system 200 calculates translation reliability (step S404). Specifically, in the translation reliability calculation unit 15 of the speech translation system 200, the original sentence described in the first language before translation, which is the speech recognition result by the speech recognition unit 212, and the reverse translation unit 14 again The reverse translation result translated into one language is input, and the distance between the two is calculated as the translation reliability. The translation reliability calculated here is the reliability for the translation process.
次に、音声翻訳システム200は、信頼度を統合する(ステップS405)。具体的には、音声翻訳システム200は、信頼度統合部21にて、入力された音声認識信頼度と翻訳信頼度とを、例えば線形補間により統合して翻訳結果に対する最終的な信頼度とする。
Next, the speech translation system 200 integrates reliability (step S405). Specifically, in the speech translation system 200, the reliability integration unit 21 integrates the input speech recognition reliability and the translation reliability by, for example, linear interpolation to obtain a final reliability for the translation result. .
図13は、本実施例における信頼度の算出例を示す説明図である。例えば、図13(a)に示すように、第一の言語である英語での入力文「what would you like to drink」に対し、音声認識結果が「what would you like to drink」であり、その音声認識信頼度は完全正解であるので文(発話全体)単位で0.99であったとする。また、音声認識結果を原文として第二の言語である日本語への翻訳結果が「何を飲みたいですか(nani wo nomitaidesuka)」であり、その逆翻訳結果が「What would you like to drink?」であったとする。このとき、翻訳信頼度は、逆翻訳結果が音声認識結果である原文を完全に再現されているため1.0となった。そのような場合に、これら音声認識信頼度と翻訳信頼度を一定の重みにおいて線形補間すると、統合した信頼度は0.99となる。
FIG. 13 is an explanatory diagram showing an example of calculation of reliability in this embodiment. For example, as shown in FIG. 13A, for an input sentence “what would you like to drink” in English, which is the first language, the speech recognition result is “what would you like to drink” Since the speech recognition reliability is completely correct, it is assumed that it is 0.99 in units of sentences (entire utterances). Moreover, the translation result into Japanese, which is the second language, based on the speech recognition result is “What do you want to drink (nani wo nomitaidesuka)” and the reverse translation result is “What would you like to drink? ”. At this time, the translation reliability was 1.0 because the original text whose reverse translation result was the speech recognition result was completely reproduced. In such a case, when these speech recognition reliability and translation reliability are linearly interpolated with a constant weight, the integrated reliability is 0.99.
一方、図13(b)の例を参照すると、第一の言語である英語での入力文「you can check in two hours before the departure time」に対し、音声認識結果が「you can check into wars before the departure time 」であり、その音声認識信頼度は誤りを含んでいるので0.79であったとする。また、音声認識結果を原文として第二の言語である日本語への翻訳結果が「出発時刻の前に戦争をチェックできます(shuppatsu jikoku no mae ni sensou wo check dekimasu)」であり、その逆翻訳結果が「I can check a war before the departure time.」であったとする。このとき、翻訳信頼度は、逆翻訳結果が音声認識結果である原文とは異なり、誤りを含んでいるため0.67となった。そのような場合に、これら音声認識信頼度と翻訳信頼度を一定の重みにおいて線形補間すると、統合した信頼度は0.77となる。
On the other hand, referring to the example of FIG. 13B, the speech recognition result is “you can check into wars before” for the input sentence “you can check in two hours before the departure time” in the first language. the departure time ”, and the speech recognition reliability includes an error, and is 0.79. In addition, the translation result into Japanese, which is the second language, using the speech recognition result as the original text is “You can check the war before the departure time (shuppatsu jikoku no mae ni sensou wo check dekimasu)” and its reverse translation Suppose the result is "I can check a war before the departure time." At this time, the translation reliability is 0.67 because the reverse translation result includes an error, unlike the original text in which the speech recognition result is obtained. In such a case, when these speech recognition reliability and translation reliability are linearly interpolated with a constant weight, the integrated reliability is 0.77.
また、図13(c)の例を参照すると、第一の言語である英語での入力文「I'll watch over your bags 」に対し、音声認識結果が「I'll walk to the bank 」であり、その音声認識信頼度は0.64であったとする。また、音声認識結果を原文として第二の言語である中国語への翻訳結果が図中のとおりであり、その逆翻訳結果が「I'll walk to the bank 」であったとする。このとき、翻訳信頼度は、逆翻訳結果が音声認識結果である原文を完全に再現しており、1.0となった。そのような場合に、これら音声認識信頼度と翻訳信頼度を一定の重みにおいて線形補間すると、統合した信頼度は0.71となる。
In addition, referring to the example of FIG. 13C, for the input sentence “I'll watch over your bags” in English, which is the first language, the speech recognition result is “I'll walk to the bank”. It is assumed that the voice recognition reliability is 0.64. In addition, it is assumed that the translation result into the second language, Chinese, using the speech recognition result as the original text is as shown in the figure, and the reverse translation result is “I'll walk to the bank”. At this time, the translation reliability was 1.0, which is a complete reproduction of the original text whose reverse translation result is the speech recognition result. In such a case, if these speech recognition reliability and translation reliability are linearly interpolated with a constant weight, the integrated reliability is 0.71.
また、図13(d)の例を参照すると、第一の言語である英語での入力文「um do you have chairs for children」に対し、音声認識結果が「do you have chairs for children 」であり、その音声認識信頼度は0.94であったとする。また、音声認識結果を原文として第二の言語である中国語への翻訳結果が図中のとおりであり、その逆翻訳結果が「Is there a lecture of a child?」であったとする。このとき、翻訳信頼度は、逆翻訳結果が音声認識結果である原文とは異なり、誤りを含んでいるため0.0となった。そのような場合に、これら音声認識信頼度と翻訳信頼度を一定の重みにおいて線形補間すると、統合した信頼度は0.75となる。
In addition, referring to the example of FIG. 13D, the speech recognition result is “do you have chairs for children” for the input sentence “um do you have chairs for children” in the first language, English. Suppose that the voice recognition reliability is 0.94. Also, assume that the result of translation into the second language, Chinese, using the speech recognition result as the original text is as shown in the figure, and the reverse translation result is “IsIthere a lecture of a child?”. At this time, the translation reliability was set to 0.0 because the reverse translation result was different from the original sentence that was the speech recognition result and contained an error. In such a case, when these speech recognition reliability and translation reliability are linearly interpolated with a constant weight, the integrated reliability is 0.75.
次に、音声翻訳システム200は、結果判定を行う(ステップS406)。具体的には、音声翻訳システム200は、結果判定部220において、機械翻訳部13から入力される翻訳結果の訳文を出力すべきかどうかを、信頼度統合部21から入力される統合信頼度に応じて判定する。
Next, the speech translation system 200 performs a result determination (step S406). Specifically, the speech translation system 200 determines whether the result determination unit 220 should output the translation of the translation result input from the machine translation unit 13 according to the integrated reliability input from the reliability integration unit 21. Judgment.
例えば、図13(a)の例では、音声認識結果と機械翻訳結果とが共に正しく、統合信頼度(図中では音声翻訳信頼度と表記)は0.99と高いため、受理すなわち出力可として判定する。一方、図13(b)の例では、音声認識結果と機械翻訳結果とが共に誤りを含み、統合信頼度は0.77と十分に高くないため(具体的には、所定の閾値より低いため)、棄却すなわち出力不可と判定する。
For example, in the example of FIG. 13 (a), both the speech recognition result and the machine translation result are correct, and the integrated reliability (denoted as speech translation reliability in the figure) is as high as 0.99. judge. On the other hand, in the example of FIG. 13B, both the speech recognition result and the machine translation result include an error, and the integrated reliability is not sufficiently high as 0.77 (specifically, it is lower than a predetermined threshold). ), It is determined that it is rejected, that is, output is impossible.
また、図13(c)の例では、機械翻訳結果は正しいが音声認識結果に誤りを含み、また図13(d)の例では、音声認識はほぼ正しいが翻訳結果に誤りを含み、いずれの例においても統合信頼度が0.77と十分に高くないため、棄却すなわち出力不可と判定する。
In the example of FIG. 13C, the machine translation result is correct but the speech recognition result includes an error. In the example of FIG. 13D, the speech recognition is almost correct but the translation result includes an error. Also in the example, since the integrated reliability is not sufficiently high as 0.77, it is determined that rejection, that is, output is impossible.
次に、音声翻訳システム200は、結果を出力する(ステップS407)。具体的には、音声翻訳システム200は、結果判定部220での判定の結果得られた翻訳結果を、出力部12を介して出力することで、例えばディスプレイ等に表示する。
Next, the speech translation system 200 outputs the result (step S407). Specifically, the speech translation system 200 outputs the translation result obtained as a result of the determination by the result determination unit 220 via the output unit 12, thereby displaying the result on a display or the like, for example.
例えば、図13(d)の例を参照すると、入力音声が「um do you have chairs for children」であったにも関わらず逆翻訳結果として「Is there a lecture of a child?」となり、低信頼度となっている。このとき、例えば図10に示すような信頼度提示部17を備えていた場合、信頼度提出部17が、逆翻訳部14で得られる逆翻訳結果と、信頼度統合部21で得られた信頼度とをあわせて提示することで、話し手側すなわち英語側のユーザに、低信頼度となった原因やその箇所を推定させることができる。またその結果、その部分の言い直しや言い換えを行わせることができる。すなわち、話し手であるユーザが逆翻訳結果を原文の言語で確認することで、翻訳対象とした中国語の翻訳結果を理解できなくても、低信頼度になった原因として「chairs」が「lecture 」となってしまったことが容易に推測できる。このため、この部分を言い換えることによって高い信頼度の獲得すなわちコミュニケーションの破綻を低減できる可能性が高まる。
For example, referring to the example of FIG. 13 (d), although the input speech is “um do you have chairs for children”, the reverse translation result is “Is there a lecture of a child?” It is a degree. At this time, for example, when the reliability presentation unit 17 as shown in FIG. 10 is provided, the reliability submission unit 17 receives the reverse translation result obtained by the reverse translation unit 14 and the reliability obtained by the reliability integration unit 21. By presenting together with the degree, it is possible to cause the speaker side, that is, the English side user to estimate the cause of the low reliability and its location. As a result, the part can be reworded or rephrased. In other words, even if the user who is the speaker does not understand the translation result of the target Chinese by confirming the reverse translation result in the original language, “chairs” is “lecture” Can be easily guessed. For this reason, in other words, there is a high possibility that high reliability, that is, communication failure can be reduced by paraphrasing this part.
なお、このとき信頼度提示部17にて提示する信頼度は、文(または発話全体)単位である必要はなく、例えば単語単位に提示してもよい。その方が言い換え箇所の同定が容易になることもある。その場合、信頼度統合部21における音声認識信頼度と翻訳信頼度の統合を、まず単語単位に行った後に文単位に拡張すればよい。
Note that the reliability presented by the reliability presentation unit 17 at this time does not have to be in units of sentences (or the entire utterance), and may be presented in units of words, for example. This may make it easier to identify the paraphrase. In that case, the integration of the speech recognition reliability and the translation reliability in the reliability integration unit 21 may be first performed for each word and then expanded for each sentence.
例えば、図13(d)の例においては、「chairs」または「do you have 」の部分の信頼度が低いことを提示すれば、その部分に問題があることを話し手側のユーザが確認でき、その箇所を別の単語や表現に言い換えるといった対策が容易になる。
For example, in the example of FIG. 13D, if the reliability of the “chairs” or “do you have” part is presented, the user on the speaker side can confirm that there is a problem in the part, It is easy to take measures such as rephrasing the part with another word or expression.
このように、本実施例では、音声を入力とする音声翻訳システムにおいて、音声認識と機械翻訳の信頼度を適切に統合して提示することで、高い信頼度の翻訳結果を出力することができる。また、ユーザにとって再入力の必要性や再入力箇所を明確にすることができる。その結果コミュニケーションの破綻を低減することができる。
As described above, in this embodiment, in a speech translation system using speech as an input, it is possible to output a translation result with high reliability by appropriately integrating and presenting the reliability of speech recognition and machine translation. . Further, it is possible for the user to clarify the necessity of re-input and the re-input part. As a result, communication failures can be reduced.
次に、本発明の概要を説明する。図14は、本発明の概要を示すブロック図である。図14に示すように、本発明による信頼度算出装置は、翻訳手段501と、逆翻訳手段502と、翻訳信頼度計算手段503と、信頼度提示手段504とを備えている。
Next, the outline of the present invention will be described. FIG. 14 is a block diagram showing an outline of the present invention. As shown in FIG. 14, the reliability calculation apparatus according to the present invention includes a translation unit 501, a reverse translation unit 502, a translation reliability calculation unit 503, and a reliability presentation unit 504.
翻訳手段501(例えば、機械翻訳部13)は、入力文に対して、入力文の言語である第一の言語とは異なる言語である第二の言語への翻訳処理を行う。
The translation unit 501 (for example, the machine translation unit 13) performs a translation process on the input sentence into a second language that is different from the first language that is the language of the input sentence.
逆翻訳手段502(例えば、逆翻訳部14)は、翻訳手段501による翻訳処理の結果得られる翻訳結果に対して、入力文の言語である第一の言語への逆翻訳処理を行う。
The reverse translation unit 502 (for example, the reverse translation unit 14) performs reverse translation processing on the translation result obtained as a result of translation processing by the translation unit 501 into the first language that is the language of the input sentence.
翻訳信頼度計算手段503(例えば、翻訳信頼度計算部15)は、入力文と逆翻訳手段502による逆翻訳処理の結果得られる逆翻訳結果との距離に基づいて、翻訳信頼度を算出する。
The translation reliability calculation unit 503 (for example, the translation reliability calculation unit 15) calculates the translation reliability based on the distance between the input sentence and the reverse translation result obtained as a result of the reverse translation process by the reverse translation unit 502.
信頼度提示手段504(例えば、信頼度提示部17および出力部12)は、入力文、翻訳結果および逆翻訳結果のうち少なくとも1つ以上を、その入力文、翻訳結果または逆翻訳結果に対応する信頼度とともにユーザに提示する。その際、翻訳信頼度が所定の閾値以下であった場合には、少なくとも入力文または逆翻訳結果を、翻訳信頼度とともに第一の言語を入力した側のユーザに提示する。
The reliability presentation unit 504 (for example, the reliability presentation unit 17 and the output unit 12) corresponds to at least one of the input sentence, the translation result, and the reverse translation result to the input sentence, the translation result, or the reverse translation result. Present to the user along with the reliability. At that time, if the translation reliability is equal to or less than a predetermined threshold, at least the input sentence or the reverse translation result is presented to the user who has input the first language together with the translation reliability.
なお、「当該(提示する)単語または単語列に対応する信頼度」とは、例えば、原文や逆翻訳結果を提示する場合には、原文と逆翻訳結果との比較によりその単語または単語列に対して算出された翻訳信頼度やその翻訳信頼度と認識信頼度とを組み合わせた統合信頼度である。また例えば翻訳結果を提示する場合には、その単語または単語列を翻訳する際に元となった原文の単語または単語列に対して算出された翻訳信頼度や統合信頼度である。
The “reliability corresponding to the (presented) word or word string” refers to, for example, when the original text or the reverse translation result is presented, the word or word string is compared with the original text and the reverse translation result. It is the integrated reliability that combines the calculated translation reliability and the translation reliability and the recognition reliability. Further, for example, when presenting a translation result, the translation reliability or the integrated reliability calculated for the original sentence word or word string that was used when the word or word string was translated.
また、本発明による信頼度算出装置が、音声入力等のテキスト入力以外の方法で入力された文または文章データに対して、認識処理を行った結果であるテキストを翻訳手段501への入力文とする信頼度算出装置である場合には、入力文に対する認識処理の信頼度と、翻訳信頼度計算手段503により算出された翻訳信頼度とを用いて、統合信頼度を計算する統合信頼度計算手段(例えば、信頼度統合部21)を備えていてもよい。そのような構成において、信頼度提示手段504は、統合信頼度が所定の閾値以下であった場合には、少なくとも入力文または逆翻訳結果を、統合信頼度または翻訳信頼度とともに第一の言語を入力した側のユーザに提示してもよい。
In addition, the reliability calculation apparatus according to the present invention converts a text, which is a result of performing recognition processing on a sentence or sentence data input by a method other than text input such as voice input, as an input sentence to the translation unit 501. In the case of the reliability calculation device, the integrated reliability calculation means for calculating the integrated reliability using the reliability of the recognition process for the input sentence and the translation reliability calculated by the translation reliability calculation means 503. (For example, the reliability integration unit 21) may be provided. In such a configuration, when the integrated reliability is equal to or lower than a predetermined threshold, the reliability presentation unit 504 outputs at least the input sentence or the reverse translation result together with the integrated reliability or the translation reliability as the first language. You may show to the user of the input side.
また、翻訳信頼度計算手段503は、入力文と逆翻訳手段による逆翻訳結果との距離を、共有N-gramを用いて求めてもよい。
Also, the translation reliability calculation means 503 may obtain the distance between the input sentence and the reverse translation result by the reverse translation means using the shared N-gram.
また、翻訳信頼度計算手段503は、翻訳信頼度を単語または単語列単位で求めるとともに、文単位の翻訳信頼度を正規化により求めてもよい。そのような構成において、信頼度提示手段504は、統合信頼度または翻訳信頼度が所定の閾値以下であった場合には、少なくとも入力文または逆翻訳結果を、当該入力文または逆翻訳結果の各単語または単語列に対応する信頼度とともに第一の言語を入力した側のユーザに提示してもよい。さらに、信頼度提示手段504は、入力文、翻訳結果および逆翻訳結果のうち少なくとも1つ以上をユーザに提示する際に、当該入力文、翻訳結果または逆翻訳結果の各単語または単語列に対応する信頼度に基づき一文内での低信頼度区間を強調して提示してもよい。
Further, the translation reliability calculation means 503 may obtain the translation reliability in units of words or word strings, and may obtain the translation reliability in units of sentences by normalization. In such a configuration, when the integrated reliability or the translation reliability is equal to or lower than a predetermined threshold, the reliability presenting means 504 outputs at least the input sentence or the reverse translation result for each of the input sentence or the reverse translation result. You may show to the user who input the 1st language with the reliability corresponding to a word or a word string. Further, the reliability degree presentation unit 504 corresponds to each word or word string of the input sentence, the translation result, or the reverse translation result when presenting at least one of the input sentence, the translation result, and the reverse translation result to the user. The low confidence interval in one sentence may be emphasized and presented based on the confidence level.
また、本発明による信頼度算出装置は、入力文および逆翻訳結果のうち少なくともいずれかに対して、同義語展開を行う同義語展開手段(例えば、同義語展開部161および同義語辞書162)を備えていてもよい。そのような構成において、翻訳信頼度計算手段503は、同義語展開後の入力文と逆翻訳結果の組み合わせについて、それぞれ距離を求め、求めた距離に基づき翻訳信頼度を算出してもよい。さらに、同義語展開手段は、認識処理に用いられる認識辞書と、翻訳処理および逆翻訳処理に用いられる翻訳辞書とが共通に保有する単語または単語列のみを対象として同義語展開を行ってもよい。
The reliability calculation device according to the present invention further includes synonym expansion means (for example, synonym expansion unit 161 and synonym dictionary 162) that performs synonym expansion on at least one of the input sentence and the reverse translation result. You may have. In such a configuration, the translation reliability calculation unit 503 may calculate the distance for each combination of the input sentence after the synonym expansion and the reverse translation result, and calculate the translation reliability based on the calculated distance. Further, the synonym expansion means may perform synonym expansion only for words or word strings that are commonly held in the recognition dictionary used in the recognition process and the translation dictionary used in the translation process and the reverse translation process. .
上記の実施形態およびその変形例の一部または全部は、以下の付記のようにも記載され得るが、以下に限定されるわけではない。
Some or all of the above-described embodiment and its modifications may be described as in the following supplementary notes, but are not limited to the following.
(付記1)入力文に対して、入力文の言語である第一の言語とは異なる言語である第二の言語への翻訳処理を行う翻訳部と、前記翻訳処理の結果得られる翻訳結果に対して、入力文の言語である第一の言語への逆翻訳処理を行う逆翻訳部と、前記入力文と前記逆翻訳処理の結果得られる逆翻訳結果との距離に基づいて、翻訳信頼度を算出する翻訳信頼度計算部と、前記入力文、翻訳結果および逆翻訳結果のうち少なくとも1つ以上を、当該入力文、翻訳結果または逆翻訳結果に対応する信頼度とともにユーザに提示する信頼度提示部とを備え、前記信頼度提示部は、前記翻訳信頼度が所定の閾値以下であった場合には、少なくとも入力文または逆翻訳結果を、翻訳信頼度とともに第一の言語を入力した側のユーザに提示することを特徴とする信頼度算出装置。
(Supplementary note 1) For the input sentence, a translation unit that performs translation processing into a second language that is different from the first language that is the language of the input sentence, and a translation result obtained as a result of the translation process On the other hand, based on the distance between the reverse translation unit that performs the reverse translation process to the first language that is the language of the input sentence, and the reverse translation result obtained as a result of the reverse translation process, the translation reliability And a reliability of presenting at least one or more of the input sentence, the translation result and the reverse translation result together with a reliability corresponding to the input sentence, the translation result or the reverse translation result to the user. A presentation unit, and when the translation reliability is less than or equal to a predetermined threshold, the reliability presentation unit inputs at least the input sentence or the reverse translation result together with the translation reliability to the first language. Presented to users of Yoriyukido calculation device.
(付記2)テキスト入力以外の方法で入力された第一の言語による文または文章データに対して、認識処理を行った結果であるテキストを翻訳部への入力文とする信頼度算出装置であって、前記入力文に対する認識処理の信頼度と、前記翻訳信頼度計算部により算出された翻訳信頼度とを用いて、統合信頼度を計算する統合信頼度計算部を備え、信頼度提示部は、前記統合信頼度が所定の閾値以下であった場合には、少なくとも入力文または逆翻訳結果を、前記統合信頼度または翻訳信頼度とともに第一の言語を入力した側のユーザに提示する付記1に記載の信頼度算出装置。
(Supplementary Note 2) A reliability calculation device that uses a text that is a result of recognition processing for sentence or sentence data in a first language input by a method other than text input, as an input sentence to the translation unit. Using the reliability of the recognition process for the input sentence and the translation reliability calculated by the translation reliability calculation unit, the integrated reliability calculation unit for calculating the integrated reliability, the reliability presentation unit is When the integrated reliability is equal to or lower than a predetermined threshold, at least the input sentence or the reverse translation result is presented to the user who has input the first language together with the integrated reliability or the translation reliability. The reliability calculation apparatus described in 1.
(付記3)翻訳信頼度計算部は、入力文と逆翻訳部による逆翻訳結果との距離を、共有N-gramを用いて求める付記1または付記2に記載の信頼度算出装置。
(Additional remark 3) The reliability calculation apparatus of Additional remark 1 or Additional remark 2 which a translation reliability calculation part calculates | requires the distance of an input sentence and the reverse translation result by a reverse translation part using shared N-gram.
(付記4)翻訳信頼度計算部は、翻訳信頼度を単語または単語列単位で求めるとともに、文単位の翻訳信頼度を正規化により求め、信頼度提示部は、統合信頼度または翻訳信頼度が所定の閾値以下であった場合には、少なくとも入力文または逆翻訳結果を、当該入力文または逆翻訳結果の各単語または単語列に対応する信頼度とともに第一の言語を入力した側のユーザに提示する付記1から付記3のうちのいずれかに記載の信頼度算出装置。
(Supplementary Note 4) The translation reliability calculation unit obtains the translation reliability in units of words or word strings and obtains the translation reliability in units of sentences by normalization, and the reliability presentation unit has the integrated reliability or the translation reliability. If it is less than or equal to a predetermined threshold, at least the input sentence or reverse translation result is sent to the user who has input the first language together with the reliability corresponding to each word or word string of the input sentence or reverse translation result. The reliability calculation apparatus according to any one of Supplementary Note 1 to Supplementary Note 3 to be presented.
(付記5)信頼度提示部は、入力文、翻訳結果および逆翻訳結果のうち少なくとも1つ以上を第一の言語をユーザに提示する際に、当該入力文、翻訳結果または逆翻訳結果の各単語または単語列に対応する信頼度に基づき一文内での低信頼度区間を強調して提示する付記4に記載の信頼度算出装置。
(Additional remark 5) When a reliability presentation part shows a 1st language to a user at least 1 or more among an input sentence, a translation result, and a back translation result, each of the said input sentence, a translation result, or a back translation result The reliability calculation apparatus according to appendix 4, wherein the low reliability interval in one sentence is emphasized and presented based on the reliability corresponding to the word or the word string.
(付記6)入力文および逆翻訳結果のうち少なくともいずれかに対して、同義語展開を行う同義語展開部を備え、翻訳信頼度計算部は、同義語展開後の入力文と逆翻訳結果の組み合わせについて、それぞれ距離を求め、求めた距離に基づき翻訳信頼度を算出する付記1から付記5のうちのいずれかに記載の信頼度算出装置。
(Supplementary Note 6) A synonym expansion unit that performs synonym expansion on at least one of the input sentence and the reverse translation result is provided, and the translation reliability calculation unit is configured to display the input sentence after the synonym expansion and the reverse translation result The reliability calculation apparatus according to any one of appendix 1 to appendix 5, which calculates a distance for each combination and calculates a translation reliability based on the calculated distance.
(付記7)テキスト入力以外の方法で入力された文に対して、認識処理を行った結果であるテキストを翻訳部への入力文とする信頼度算出装置であって、同義語展開部は、認識処理に用いられる認識辞書と、翻訳処理および逆翻訳処理に用いられる翻訳辞書とが共通に保有する単語または単語列のみを対象として同義語展開を行う付記6に記載の信頼度算出装置。
(Additional remark 7) It is the reliability calculation apparatus which makes the text which is the result of having performed the recognition process with respect to the sentence input by methods other than text input as an input sentence to a translation part, Comprising: The reliability calculation apparatus according to appendix 6, wherein synonym expansion is performed only for words or word strings that are commonly held in a recognition dictionary used for recognition processing and a translation dictionary used for translation processing and reverse translation processing.
この出願は、2011年7月28日に出願された日本特許出願2011-165708を基礎とする優先権を主張し、その開示の全てをここに取り込む。
This application claims priority based on Japanese Patent Application 2011-165708 filed on July 28, 2011, the entire disclosure of which is incorporated herein.
以上、実施形態を参照して本願発明を説明したが、本願発明は上記の実施形態に限定されるものではない。本願発明の構成や詳細には、本願発明のスコープ内で当業者が理解し得る様々な変更をすることができる。
The present invention has been described above with reference to the embodiments, but the present invention is not limited to the above-described embodiments. Various changes that can be understood by those skilled in the art can be made to the configuration and details of the present invention within the scope of the present invention.
本発明は、テキストデータ形式で入力された文または文章に対して翻訳処理を行う翻訳装置だけでなく、音声入力されて、またはOCRやタッチパネルを用いて文または文章データが入力されて、認識処理を経た後に翻訳処理を行うような翻訳装置においても、好適に適用可能である。
The present invention is not limited to a translation device that performs a translation process on a sentence or sentence input in a text data format, but also a speech input or a sentence or sentence data input using an OCR or a touch panel, and a recognition process. The present invention can also be suitably applied to a translation apparatus that performs translation processing after passing through.
10、10b、10c、10d、10e、10f 信頼度算出装置、信頼度算出部
11 入力部
12 出力部
13 機械翻訳部
14 逆翻訳部
15 翻訳信頼度計算部
161 同義語展開部
162 同義語辞書
17 信頼度提示部
100 機械翻訳装置
110、220 結果判定部
200 音声翻訳システム
210 音声認識結果入力部
211 音声入力部
212 音声認識部
21 信頼度統合部
501 翻訳手段
502 逆翻訳手段
503 翻訳信頼度計算手段
504 信頼度提示手段 10, 10b, 10c, 10d, 10e, 10f Reliability calculation device,reliability calculation unit 11 input unit 12 output unit 13 machine translation unit 14 reverse translation unit 15 translation reliability calculation unit 161 synonym expansion unit 162 synonym dictionary 17 Reliability presentation unit 100 machine translation device 110, 220 result determination unit 200 speech translation system 210 speech recognition result input unit 211 speech input unit 212 speech recognition unit 21 reliability integration unit 501 translation unit 502 reverse translation unit 503 translation reliability calculation unit 504 Reliability presentation means
11 入力部
12 出力部
13 機械翻訳部
14 逆翻訳部
15 翻訳信頼度計算部
161 同義語展開部
162 同義語辞書
17 信頼度提示部
100 機械翻訳装置
110、220 結果判定部
200 音声翻訳システム
210 音声認識結果入力部
211 音声入力部
212 音声認識部
21 信頼度統合部
501 翻訳手段
502 逆翻訳手段
503 翻訳信頼度計算手段
504 信頼度提示手段 10, 10b, 10c, 10d, 10e, 10f Reliability calculation device,
Claims (9)
- 入力文に対して、入力文の言語である第一の言語とは異なる言語である第二の言語への翻訳処理を行う翻訳手段と、
前記翻訳処理の結果得られる翻訳結果に対して、入力文の言語である第一の言語への逆翻訳処理を行う逆翻訳手段と、
前記入力文と前記逆翻訳処理の結果得られる逆翻訳結果との距離に基づいて、翻訳信頼度を算出する翻訳信頼度計算手段と、
前記入力文、翻訳結果および逆翻訳結果のうち少なくとも1つ以上を、当該入力文、翻訳結果または逆翻訳結果に対応する信頼度とともにユーザに提示する信頼度提示手段とを備え、
前記信頼度提示手段は、前記翻訳信頼度が所定の閾値以下であった場合には、少なくとも入力文または逆翻訳結果を、翻訳信頼度とともに第一の言語を入力した側のユーザに提示する
ことを特徴とする信頼度算出装置。 Translation means for performing a translation process on the input sentence to a second language that is different from the first language that is the language of the input sentence;
Reverse translation means for performing reverse translation processing to the first language that is the language of the input sentence, on the translation result obtained as a result of the translation processing;
A translation reliability calculation means for calculating a translation reliability based on the distance between the input sentence and the reverse translation result obtained as a result of the reverse translation process;
A reliability degree presentation unit that presents at least one or more of the input sentence, the translation result, and the reverse translation result together with a reliability corresponding to the input sentence, the translation result, or the reverse translation result;
When the translation reliability is equal to or lower than a predetermined threshold, the reliability presentation means presents at least an input sentence or a reverse translation result to the user who has input the first language together with the translation reliability. The reliability calculation apparatus characterized by this. - テキスト入力以外の方法で入力された第一の言語による文または文章データに対して、認識処理を行った結果であるテキストを翻訳手段への入力文とする信頼度算出装置であって、
前記入力文に対する認識処理の信頼度と、前記翻訳信頼度計算手段により算出された翻訳信頼度とを用いて、統合信頼度を計算する統合信頼度計算手段を備え、
信頼度提示手段は、前記統合信頼度が所定の閾値以下であった場合には、少なくとも入力文または逆翻訳結果を、前記統合信頼度または翻訳信頼度とともに第一の言語を入力した側のユーザに提示する
請求項1に記載の信頼度算出装置。 A reliability calculation device that uses a text that is a result of recognition processing for a sentence or sentence data in a first language that is input by a method other than text input, as an input sentence to the translation means,
Using the reliability of the recognition process for the input sentence and the translation reliability calculated by the translation reliability calculation means, comprising integrated reliability calculation means for calculating the integrated reliability;
When the integrated reliability is equal to or less than a predetermined threshold, the reliability presenting means provides at least an input sentence or a reverse translation result as a user who has input the first language together with the integrated reliability or the translation reliability. The reliability calculation device according to claim 1. - 翻訳信頼度計算手段は、入力文と逆翻訳手段による逆翻訳結果との距離を、共有N-gramを用いて求める
請求項1または請求項2に記載の信頼度算出装置。 The reliability calculation device according to claim 1 or 2, wherein the translation reliability calculation means obtains the distance between the input sentence and the reverse translation result by the reverse translation means using a shared N-gram. - 翻訳信頼度計算手段は、翻訳信頼度を単語または単語列単位で求めるとともに、文単位の翻訳信頼度を正規化により求め、
信頼度提示手段は、統合信頼度または翻訳信頼度が所定の閾値以下であった場合には、少なくとも入力文または逆翻訳結果を、当該入力文または逆翻訳結果の各単語または単語列に対応する信頼度とともに第一の言語を入力した側のユーザに提示する
請求項1から請求項3のうちのいずれか1項に記載の信頼度算出装置。 The translation reliability calculation means calculates the translation reliability in units of words or word strings, and calculates the translation reliability in units of sentences by normalization,
When the integrated reliability or the translation reliability is equal to or less than a predetermined threshold, the reliability presenting means corresponds at least the input sentence or the reverse translation result to each word or word string of the input sentence or the reverse translation result. The reliability calculation apparatus according to any one of claims 1 to 3, wherein the reliability is presented to a user who inputs the first language together with the reliability. - 信頼度提示手段は、入力文、翻訳結果および逆翻訳結果のうち少なくとも1つ以上を第一の言語をユーザに提示する際に、当該入力文、翻訳結果または逆翻訳結果の各単語または単語列に対応する信頼度に基づき一文内での低信頼度区間を強調して提示する
請求項4に記載の信頼度算出装置。 When presenting at least one or more of the input sentence, the translation result, and the reverse translation result to the user in the first language, the reliability degree presentation means each word or word string of the input sentence, the translation result, or the reverse translation result. The reliability calculation apparatus according to claim 4, wherein a low reliability section in one sentence is emphasized and presented based on the reliability corresponding to. - 入力文および逆翻訳結果のうち少なくともいずれかに対して、同義語展開を行う同義語展開手段を備え、
翻訳信頼度計算手段は、同義語展開後の入力文と逆翻訳結果の組み合わせについて、それぞれ距離を求め、求めた距離に基づき翻訳信頼度を算出する
請求項1から請求項5のうちのいずれか1項に記載の信頼度算出装置。 Synonym expansion means for performing synonym expansion on at least one of the input sentence and the reverse translation result,
The translation reliability calculation means calculates a distance for each combination of the input sentence after the synonym expansion and the reverse translation result, and calculates the translation reliability based on the calculated distance. The reliability calculation apparatus according to item 1. - テキスト入力以外の方法で入力された文に対して、認識処理を行った結果であるテキストを翻訳手段への入力文とする信頼度算出装置であって、
同義語展開手段は、認識処理に用いられる認識辞書と、翻訳処理および逆翻訳処理に用いられる翻訳辞書とが共通に保有する単語または単語列のみを対象として同義語展開を行う
請求項6に記載の信頼度算出装置。 A reliability calculation apparatus that uses a text that is a result of recognition processing for a sentence input by a method other than text input as an input sentence to the translation means,
The synonym expansion means expands synonyms only for words or word strings that are commonly held in a recognition dictionary used for recognition processing and a translation dictionary used for translation processing and reverse translation processing. Reliability calculation device. - 入力文に対して、入力文の言語である第一の言語とは異なる言語である第二の言語への翻訳処理を行い、
前記翻訳処理の結果得られる翻訳結果に対して、入力文の言語である第一の言語への逆翻訳処理を行い、
前記入力文と前記逆翻訳処理の結果得られる逆翻訳結果との距離に基づいて、翻訳信頼度を算出し、
前記入力文、翻訳結果および逆翻訳結果のうち少なくとも1つ以上を、当該入力文、翻訳結果または逆翻訳結果に対応する信頼度とともにユーザに提示する際に、前記翻訳信頼度が所定の閾値以下であった場合には、少なくとも入力文または逆翻訳結果を、翻訳信頼度とともに第一の言語を入力した側のユーザに提示する
ことを特徴とする翻訳信頼度算出利用方法。 The input sentence is translated into a second language that is different from the first language that is the language of the input sentence,
For the translation result obtained as a result of the translation process, perform a reverse translation process to the first language that is the language of the input sentence,
Based on the distance between the input sentence and the reverse translation result obtained as a result of the reverse translation process, the translation reliability is calculated,
When presenting to the user at least one or more of the input sentence, translation result and reverse translation result together with the reliability corresponding to the input sentence, translation result or reverse translation result, the translation reliability is below a predetermined threshold A translation reliability calculation and utilization method, wherein at least the input sentence or the reverse translation result is presented to the user who has input the first language together with the translation reliability. - コンピュータに、
第一の言語で記述された入力文を、第一の言語とは異なる言語である第二の言語に変換する翻訳処理、
前記翻訳処理の結果得られる翻訳結果を、入力文の言語である第一の言語に変換する逆翻訳処理、
前記入力文と前記逆翻訳処理の結果得られる逆翻訳結果との距離に基づいて、翻訳信頼度を算出する翻訳信頼度算出処理、および
前記入力文、翻訳結果および逆翻訳結果のうち少なくとも1つ以上を、当該入力文、翻訳結果または逆翻訳結果に対応する信頼度とともにユーザに提示する信頼度提示処理を実行させ、
前記信頼度提示処理で、前記翻訳信頼度が所定の閾値以下であった場合に、少なくとも入力文または逆翻訳結果を、翻訳信頼度とともに第一の言語を入力した側のユーザに提示させる
ための翻訳エンジン用プログラム。 On the computer,
A translation process for converting an input sentence written in the first language into a second language, which is a language different from the first language,
A reverse translation process for converting a translation result obtained as a result of the translation process into a first language that is a language of an input sentence;
A translation reliability calculation process for calculating a translation reliability based on a distance between the input sentence and a reverse translation result obtained as a result of the reverse translation process; and at least one of the input sentence, the translation result, and the reverse translation result The above process is executed to provide the user with the reliability corresponding to the input sentence, the translation result, or the reliability corresponding to the reverse translation result,
In the reliability presentation process, when the translation reliability is equal to or lower than a predetermined threshold, at least an input sentence or a reverse translation result is presented to a user who inputs the first language together with the translation reliability. Translation engine program.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2011165708 | 2011-07-28 | ||
JP2011-165708 | 2011-07-28 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2013014877A1 true WO2013014877A1 (en) | 2013-01-31 |
Family
ID=47600754
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2012/004541 WO2013014877A1 (en) | 2011-07-28 | 2012-07-13 | Reliability calculation device, method for using translation reliability calculation, and program for translation engine |
Country Status (2)
Country | Link |
---|---|
JP (1) | JPWO2013014877A1 (en) |
WO (1) | WO2013014877A1 (en) |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2015069600A (en) * | 2013-09-30 | 2015-04-13 | 株式会社東芝 | Voice translation system, method, and program |
JP2017058865A (en) * | 2015-09-15 | 2017-03-23 | 株式会社東芝 | Machine translation device, machine translation method, and machine translation program |
WO2017163284A1 (en) * | 2016-03-25 | 2017-09-28 | パナソニックIpマネジメント株式会社 | Translation device |
US9836457B2 (en) | 2015-05-25 | 2017-12-05 | Panasonic Intellectual Property Corporation Of America | Machine translation method for performing translation between languages |
WO2018055983A1 (en) * | 2016-09-23 | 2018-03-29 | パナソニックIpマネジメント株式会社 | Translation device, translation system, and evaluation server |
JP2018206356A (en) * | 2017-06-08 | 2018-12-27 | パナソニックIpマネジメント株式会社 | Translation information providing method, translation information providing program, and translation information providing apparatus |
JP2019003433A (en) * | 2017-06-15 | 2019-01-10 | 株式会社リクルートライフスタイル | Program, display method, and information processing device |
JP2019121241A (en) * | 2018-01-09 | 2019-07-22 | パナソニックIpマネジメント株式会社 | Translation device, translation method and program |
US10726210B2 (en) | 2017-05-15 | 2020-07-28 | Fujitsu Limited | Non-transitory computer-readable storage medium, information outputting method, and information processing apparatus |
CN111666775A (en) * | 2020-05-21 | 2020-09-15 | 平安科技(深圳)有限公司 | Text processing method, device, equipment and storage medium |
WO2021248589A1 (en) * | 2020-06-12 | 2021-12-16 | Huawei Technologies Co., Ltd. | System and method for bi-directional translation using sum-product networks |
WO2022209448A1 (en) * | 2021-03-29 | 2022-10-06 | 国立研究開発法人情報通信研究機構 | Simultaneous translation system and method |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH05266073A (en) * | 1992-03-23 | 1993-10-15 | Matsushita Electric Ind Co Ltd | Machine translation apparatus |
JP2000222406A (en) * | 1999-01-27 | 2000-08-11 | Sony Corp | Voice recognition and translation device and its method |
JP2006252323A (en) * | 2005-03-11 | 2006-09-21 | National Institute Of Information & Communication Technology | Data conversion aptitude evaluation method, and data converter |
JP2010072963A (en) * | 2008-09-18 | 2010-04-02 | Yahoo Japan Corp | Advertising bid phrase proposal apparatus, advertising bid phrase proposal system and advertising bid phrase proposal method |
-
2012
- 2012-07-13 WO PCT/JP2012/004541 patent/WO2013014877A1/en active Application Filing
- 2012-07-13 JP JP2013525566A patent/JPWO2013014877A1/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH05266073A (en) * | 1992-03-23 | 1993-10-15 | Matsushita Electric Ind Co Ltd | Machine translation apparatus |
JP2000222406A (en) * | 1999-01-27 | 2000-08-11 | Sony Corp | Voice recognition and translation device and its method |
JP2006252323A (en) * | 2005-03-11 | 2006-09-21 | National Institute Of Information & Communication Technology | Data conversion aptitude evaluation method, and data converter |
JP2010072963A (en) * | 2008-09-18 | 2010-04-02 | Yahoo Japan Corp | Advertising bid phrase proposal apparatus, advertising bid phrase proposal system and advertising bid phrase proposal method |
Non-Patent Citations (2)
Title |
---|
MAI MIYABE ET AL.: "Effects of Undertaking Translation Repair Using Back Translation", THE TRANSACTIONS OF THE INSTITUTE OF ELECTRONICS, INFORMATION AND COMMUNICATION ENGINEERS (J90-D), 1 December 2007 (2007-12-01), pages 3141 - 3150 * |
MAI MIYABE ET AL.: "Improvement Effect of Translation Repair Efficiency on Providing Translation Inadequacy Part", FIT2007 DAI 6 KAI FORUM ON INFORMATION TECHNOLOGY IPPAN KOEN RONBUNSHU, vol. 3, 22 August 2007 (2007-08-22), pages 435 - 436 * |
Cited By (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2015069600A (en) * | 2013-09-30 | 2015-04-13 | 株式会社東芝 | Voice translation system, method, and program |
US10311146B2 (en) | 2015-05-25 | 2019-06-04 | Panasonic Intellectual Property Corporation Of America | Machine translation method for performing translation between languages |
US9836457B2 (en) | 2015-05-25 | 2017-12-05 | Panasonic Intellectual Property Corporation Of America | Machine translation method for performing translation between languages |
US10061769B2 (en) | 2015-05-25 | 2018-08-28 | Panasonic Intellectual Property Corporation Of America | Machine translation method for performing translation between languages |
JP2017058865A (en) * | 2015-09-15 | 2017-03-23 | 株式会社東芝 | Machine translation device, machine translation method, and machine translation program |
JPWO2017163284A1 (en) * | 2016-03-25 | 2018-03-29 | パナソニックIpマネジメント株式会社 | Translation device |
WO2017163284A1 (en) * | 2016-03-25 | 2017-09-28 | パナソニックIpマネジメント株式会社 | Translation device |
US10671814B2 (en) | 2016-03-25 | 2020-06-02 | Panasonic Intellectual Property Management Co., Ltd. | Translation device and program recording medium |
JPWO2018055983A1 (en) * | 2016-09-23 | 2019-01-17 | パナソニックIpマネジメント株式会社 | Translation apparatus, translation system, and evaluation server |
WO2018055983A1 (en) * | 2016-09-23 | 2018-03-29 | パナソニックIpマネジメント株式会社 | Translation device, translation system, and evaluation server |
US11030418B2 (en) | 2016-09-23 | 2021-06-08 | Panasonic Intellectual Property Management Co., Ltd. | Translation device and system with utterance reinput request notification |
US10726210B2 (en) | 2017-05-15 | 2020-07-28 | Fujitsu Limited | Non-transitory computer-readable storage medium, information outputting method, and information processing apparatus |
JP2018206356A (en) * | 2017-06-08 | 2018-12-27 | パナソニックIpマネジメント株式会社 | Translation information providing method, translation information providing program, and translation information providing apparatus |
JP2019003433A (en) * | 2017-06-15 | 2019-01-10 | 株式会社リクルートライフスタイル | Program, display method, and information processing device |
JP2019121241A (en) * | 2018-01-09 | 2019-07-22 | パナソニックIpマネジメント株式会社 | Translation device, translation method and program |
CN111666775A (en) * | 2020-05-21 | 2020-09-15 | 平安科技(深圳)有限公司 | Text processing method, device, equipment and storage medium |
CN111666775B (en) * | 2020-05-21 | 2023-08-22 | 平安科技(深圳)有限公司 | Text processing method, device, equipment and storage medium |
WO2021248589A1 (en) * | 2020-06-12 | 2021-12-16 | Huawei Technologies Co., Ltd. | System and method for bi-directional translation using sum-product networks |
US11586833B2 (en) | 2020-06-12 | 2023-02-21 | Huawei Technologies Co., Ltd. | System and method for bi-directional translation using sum-product networks |
WO2022209448A1 (en) * | 2021-03-29 | 2022-10-06 | 国立研究開発法人情報通信研究機構 | Simultaneous translation system and method |
Also Published As
Publication number | Publication date |
---|---|
JPWO2013014877A1 (en) | 2015-02-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2013014877A1 (en) | Reliability calculation device, method for using translation reliability calculation, and program for translation engine | |
JP6251958B2 (en) | Utterance analysis device, voice dialogue control device, method, and program | |
JP4680691B2 (en) | Dialog system | |
JP5480760B2 (en) | Terminal device, voice recognition method and voice recognition program | |
US8275618B2 (en) | Mobile dictation correction user interface | |
KR101590724B1 (en) | Method for modifying error of speech recognition and apparatus for performing the method | |
US11942076B2 (en) | Phoneme-based contextualization for cross-lingual speech recognition in end-to-end models | |
US8566076B2 (en) | System and method for applying bridging models for robust and efficient speech to speech translation | |
US20060149551A1 (en) | Mobile dictation correction user interface | |
US20140358544A1 (en) | Systems and methods for adaptive proper name entity recognition and understanding | |
US7716039B1 (en) | Learning edit machines for robust multimodal understanding | |
US20110153309A1 (en) | Automatic interpretation apparatus and method using utterance similarity measure | |
KR20090106937A (en) | Correction System for spelling error and method thereof | |
US20130268259A1 (en) | Translation apparatus and method thereof | |
JP5558284B2 (en) | Speech recognition system, speech recognition method, and speech recognition program | |
JP2008243080A (en) | Device, method, and program for translating voice | |
WO2012004955A1 (en) | Text correction method and recognition method | |
Rabiner et al. | Speech recognition: Statistical methods | |
JP4826719B2 (en) | Speech recognition system, speech recognition method, and speech recognition program | |
JP6001944B2 (en) | Voice command control device, voice command control method, and voice command control program | |
JP5300576B2 (en) | SEARCH DEVICE, SEARCH METHOD, AND SEARCH PROGRAM | |
Fu et al. | Automatic speech recognition based on non-uniform error criteria | |
KR20110119478A (en) | Apparatus for speech recognition and method thereof | |
JP6325770B2 (en) | Speech recognition error correction apparatus and program thereof | |
JPH11143493A (en) | Device and system for understanding voice word |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 12817761 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2013525566 Country of ref document: JP Kind code of ref document: A |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 12817761 Country of ref document: EP Kind code of ref document: A1 |