JPS62163175A - Mechanical translating device - Google Patents

Abstract

PURPOSE:To reduce the waste in the translating process and to obtain the result of translation in a short period by changing the translating process mode in case the translation is not through within a limited time. CONSTITUTION:A time setting part 4a sets a limit time for translation based on a single input original sentence to be translated. A translation processing part 4b translates the input original sentence with reference to a translation dictionary 5. In this case, the part 4b first translates just one of input sentences and then divides the original sentence into the prescribed unit of translation, e.g., paragraphs or phrases together with an original sentence dividing part 4d in case the relevant translation fails or the time needed for translation is equal to the set time. Then the translation candidates are obtained and delivered successively for each of divided translation processing units. The post-setting processing is carried out to the partial translation result through the interactive operations of an operator.

Description

DETAILED DESCRIPTION OF THE INVENTION [Technical Field of the Invention] The present invention relates to a machine translation device that improves the efficiency of translation processing and is capable of obtaining highly natural translated sentences.

[Technical background of the invention and its problems]

2. Description of the Related Art Recently, machine translation devices that automatically machine translate an input original text using a computer and obtain the translated text have been attracting attention. For example, input a Japanese sentence and get its English translation,
On the other hand, various attempts have been made to develop natural language machine translation devices that input an English sentence and obtain its Japanese translation.

Basically, this type of machine translation device performs morphological analysis, syntactic analysis, and semantic analysis of the input original text, and converts it into words (phrases).
Divide the above input original text into predetermined language processing units such as: ■ Find the translation words (translated phrases) for each language processing unit by referring to a translation dictionary that stores knowledge information necessary for translation processing, and ■ It is configured to combine translated words (translated phrases) according to predetermined translation rules to generate a translated text for the original text.

However, the expression styles of natural language are extremely diverse, and it is difficult to say that analysis techniques have been sufficiently established.

That is, syntactic analysis basically begins with selecting one part of speech from a list of parts of speech of the original language that constitutes the input original text. However, when there are a huge number of candidate part-of-speech sequences, the time required to process them becomes extremely long.

On the other hand, in the past, if the translation process described above fails, a partial translation is output for each predetermined division unit by dividing a sentence of the original text at appropriate and appropriate positions, and the partial translation is output under the instructions of the operator. It has been proposed to combine the two to complete the translation.

However, in order to perform such partial translation processing, it is necessary to wait for a long time until the above-described translation processing for the human original text is completed and it is determined whether the translation processing has failed. Such waiting time imposes a large psychological and physical burden on the operator, leading to a decrease in translation processing efficiency.

Further, the above-mentioned waiting time (time required for translation processing) is influenced by the complexity of the syntactic structure of the human original text, the length of the sentence, etc.

For this reason, there is also a problem in uniquely setting the processing time that can be spent on the translation process and discontinuing the translation process on the input original text when the set time is reached.

[Purpose of the invention]

The present invention has been made in consideration of these circumstances, and its purpose is to limit the time spent on translation processing depending on the input original text, reduce unnecessary translation processing, and improve translation efficiency. An object of the present invention is to provide a machine translation device that can improve the performance of users.

[Summary of the invention]

The present invention provides a machine translation device that translates an original text given from an input unit using knowledge information stored in a translation dictionary to obtain a translated text, which measures the translation processing time for the input original text and calculates the progress of the translation process. When the time reaches a predetermined setting time, the translation processing form is changed, and in particular, the setting time is set to -. Depending on the input original text, for example, the number of words that make up the human original text or each IP word is changed. This is determined according to the number of parts of speech that the word has, thereby shortening the time required to translate the human original text.

〔Effect of the invention〕

Thus, according to the present invention, the time spent on translation processing for an input original text is limited according to the IF 11 of the input original text, and if the translation processing is not completed within the time limit, the translation processing form is changed. It becomes possible to reduce waste in translation processing and, as a result, obtain translation results in a short time.

Therefore, it is possible to perform translation processing efficiently and obtain translation results in a short time without needing to spend an unnecessarily long time translating an input original text with a complex structure. Great effects can be achieved.

[Embodiments of the invention]

Hereinafter, one embodiment of the present invention will be described with reference to the drawings.

In this embodiment, an English sentence is input and it is machine translated into a Japanese sentence. FIG. 1 is a schematic diagram of the apparatus of this embodiment.

In FIG. 1, l is an input unit consisting of a keyboard or the like. An English sentence consisting of a character string or the like inputted through the input unit 1 is stored in the original text storage unit 2 as an original text to be subjected to translation processing.

Under the control of the editing control section 3, the translation section 4 refers to a translation dictionary 5 in which knowledge information necessary for translation processing is stored in advance, and sequentially processes the original text stored in the original text storage section 2 in a predetermined processing unit. Processed by machine translation. The translated text (Japanese in this case) obtained by the translation section 4 is managed in association with the obtained original text and stored in the translated text storage section 6.

The knowledge information stored in the translation dictionary 5 includes, for example, a rule/irregular variation dictionary 5a, a word (translation) dictionary 5b, an analysis grammar 5c, a conversion grammar 5d, a generation grammar 5e, and a morpheme generation grammar 5r.

The editing control unit 3 then drives the display control unit 7 to output the English sentence (original text) stored in the original text storage unit 2 and the Japanese sentence (, II! sentence) stored in the translated text storage unit 6. 17 on the display section 8 consisting of a CRT display or the like. By displaying the original text and the translated text on the display section 8, post-editing processing is performed on the translated text. This post-editing process is performed, for example, in accordance with control information provided from the input section 1 and by referring to knowledge information stored in the translation dictionary 5.

The printing unit 9 is for outputting a hard copy of the translated text (Japanese text) completed by the above-mentioned post-editing process.

By the way, the keyboard constituting the input section 1 is constructed as shown in FIG. 2, for example. That is, this keyboard includes, for example, in addition to a key group 1a for inputting character data, a translation instruction key II), an editing key JIIc, a function control key group 1d, and a cursor control key 7 for the display section 8. ! ile etc.

Further, FIG. 3 shows an example of the screen configuration on the display section 8. As shown in FIG. Here, at the top of the display screen is the translation editing area 8a.
The display screen is configured by setting an original text display area 81) on the left side of the screen, and a translated text display area 8c on the right side of the screen.

The -1- original text display area 8b is an area for displaying the human original text (English text) stored in the original text storage section 2.

The translation display area 8c is an area for displaying the translations (Japanese sentences) stored in the translation storage section 6 in correspondence with the original texts from which the translations were obtained.

Further, the translation editing area 8a is an area for displaying knowledge information necessary for translation processing, such as translation word candidates, searched from the translation dictionary 5.

FIG. 4 shows the basic operation sequence of the embodiment apparatus constructed in this manner.

The editing control unit 3 determines the translation completion information provided from the translation unit 4 and various key information input from the human resources unit 1, and interactively processes the information in accordance with the operation sequence shown in FIG. Controls the translation/editing process.

That is, the editing control section 3 monitors the translation processing state in the translation section 4. In step A), when the translation section 4 completes the translation processing for one original text, the editing control section 3 stores the translation obtained by the translation processing in the translation storage section 6. At the same time, the translated text is displayed on the display section 8 (step B).

If a translation completion signal is not obtained from the translation section 4, the key information given from the input section 1 is determined (steps C, D, E, F). Depending on the determination result of the key information, the following processes are controlled.

Specifically, when the input key information is a "translation instruction key" (step C), the editing control section 3 takes out one of the input original texts stored in the original text storage section 2 and sends it to the translation section 4. and starts the translation process (step G).

In this translation process, for example, as shown in the processing sequence in FIG. Analyze using dictionary 5a (
Step Q). Through this morphological analysis, for example, a language that has a conjugation change or an inflection change is converted into its original form (basic form). Specifically, it converts eight words expressed in past tense, progressive tense, and past participle form into present tense, and also converts words expressed in comparative and superlative tense into their original forms (original words).

Next, for each original word of the original text that has been morphologically analyzed as described above, information on its translated word and part of speech is obtained using the translated word dictionary 51) (step R). This process is performed by searching the translation dictionary 51 using the original word as a headword.

Thereafter, the input original text is parsed (step T) under control according to the above-mentioned parsing grammar 5c (step S). This syntactic analysis is repeated until the above-mentioned (h-sentence analysis) of the original sentence is successful.Then, through this syntactic analysis, the arrangement structure of the parts of speech of the original language that composes the original sentence, their dependencies, relations, tenses, etc. is required.

Thereafter, the structure of the parsed original sentence is converted into the syntactic structure of the translated sentence using the conversion grammar 5d (step U
). That is, the conversion grammar 5d is used to convert the syntactic structure of English (original text) into the syntactic structure of Japanese (translated text). If this conversion of the syntactic structure fails, for example, it is assumed that there is an error in the syntactic analysis t17 of the original text, and the process starts over from the syntactic analysis process of the original text.

Thereafter, the translation word candidates found for each original word of the original text based on the syntactic structure of the translation text are rearranged in word order according to the language form of the translation text to obtain translation candidates for the original text (step V).

This syntax generation process is performed according to the generation grammar 5r described above.

Then, each translation candidate (basic form) constituting the translation candidate is subjected to conjugation transformation processing and ending transformation processing according to the syntactic analysis result of the original sentence and the morpheme generation grammar 5f, and the translation is used as an appropriate linguistic expression to complete the translation. (Step W)
.

Through this series of translation processes, a translated text for the original text is obtained. Incidentally, when m number of translations are obtained for one original text, it is convenient to display only one of them and at the same time display the existence of other translations.

On the other hand, returning to FIG. 4, if the manual key information is "r character key" (step D), the character code indicated by that character key is stored in the manual buffer. The character pattern is stored in the original text storage section 2 and displayed on the display section 8 (step I).
). By displaying each character pattern of the character code stored in this manual buffer, the input original text consisting of the character string input from the input section 1 is displayed.

If the input key information is an "editing key" (step E), editing processing corresponding to the editing key is executed on the translation (step J). Similarly, if the input key information is a "function key" (step F)
, the process corresponding to the function key is executed (step K).

If the key information is not input, or if the manual key information is other than the above-mentioned "key", other processing (step L) is performed, for example, a hard copy of the translation obtained in the translation storage section 6 is performed. Output etc. are performed.

According to such an operation sequence of the editing control unit 3, for example, when an operator inputs a character by operating the character key group 1a of the keyboard, the information of the human character is sequentially set in the input buffer and used for translation processing. The original text is sequentially stored in the original text storage unit 2 (steps D and H).

The human original text is then displayed on the original text display section 8b of the display section 8 (step I).

If you operate the translation instruction key 11 at any point in character input, for example at the end of inputting a sentence, the translation process for the input original text stored in the 2-key character buffer will start according to the input key information ( Steps C, G).

When the translation process is completed, the resulting translation is displayed in the translation display area 8c of the display section 8 (steps A and B).

If the input original text needs to be corrected, in the middle of inputting the original text by manipulating the character manual key group 1a, for example, operate the cursor control key group 1e to move the cursor to the correction point, and perform correction 1E. The editing process is performed by operating the editing key group 1c for inserting, deleting, etc. Modifications are performed by key operations, for example, using auxiliary information to display candidates for modifications other than the word or phrase indicated by the cursor.

Further, editing processing for the translated text is similarly performed using function keys. These function keys can be used, for example, to display the translated word for a word in a translated sentence using the "translation display key", to display a dictionary for a word in the original text using the "dictionary display key", and to register new words and phrases in the dictionary using the "dictionary registration key". , the deletion of new words and phrases registered in the dictionary from the dictionary using the ``dictionary deletion key'', and the display of partial translations of original sentences for which translation processing has failed using the ``r partial translation key''.

In this way, the basic operations of machine translation processing are controlled.

By the way, the translation section 4 is schematically configured as shown in FIG. 6.

The time setting unit 4a sets a time limit that can be spent on the translation process based on a sentence of the human original text to be translated.

Therefore, the translation processing section 4b translates the inputted original text by referring to the translation dictionary 5.

This translation processing time) is calculated by first properly translating a sentence of the original text in -1- according to the procedure described above, and when the translation process fails or the time spent on the translation process is set in -I-. When the time is reached, the original text division processing unit 4d
A predetermined translation processing section f1'/, in cooperation with the original text, divides the original text into, for example, clauses or phrases, and obtains translation candidates for each of the divided translation processing units and sequentially outputs them.

The post-editing process for this partial translation process result is executed through interactive processing by the operator to complete the translated text.

Thus, the elapsed time measuring section 4c measures the elapsed time of translation processing for one sentence of the input original text by the translation processing section 4b, and determines whether the processing elapsed time has reached the above-mentioned set time. . If the translation processing is not completed within the set time, the translation processing unit 4b cancels the current translation processing as described in step 11 above, and instead starts the original text division processing unit 4d to perform the translation processing. The unit 4b is configured to perform partial division translation processing.

Now, the time setting section 4a sets the translation processing time according to the input original text, as shown in FIG. 7, for example. That is, when a sentence to be translated is given, the number N of 111 words making up the - sentence is counted (step a).

This counting of the number of words N is performed by, for example, cutting out the input character string into word units according to spaces and delimiters, and counting the number of words. After that, the counted number of words N is set to a predetermined value, 771. , ff 2. , f23 and determine the length of the input sentence from the magnitude relationship of the values (
Step b.

c, d).

Note that the above setting value J1. I! 2. No. 3 is, for example, (60
).

(40) and (20). As a result, there are long sentences with the number of words (60) or more, slightly longer sentences with the number of words less than (60) and (40) or more, and sentences with the number of words (40) or more.
The length of the input original sentence is determined into four types: a normal length sentence with a length of less than (20) or more, and a short sentence with a word count of less than (20).

Then, depending on the determination result (length and number of words) of this sentence, the time Sl that can be spent on the translation process of the above-mentioned sentence.

82. S 3. S4 is set to, for example, 180 seconds, 120 seconds, 9() seconds, and 60 seconds, respectively (steps e, f, g, h).

In other words, the translation processing time is set according to the number of words N, which is the length of the input original text, as shown in the following table.

Therefore, in this example, for example, if the number of Lli words in the - sentence is N (48
), the time limit for translation processing for that - sentence is set as 120 seconds.

Note that the complexity of the input original text is not necessarily determined only by the length of the sentence based on the number of words. For example, it is common for each word to have multiple parts of speech, and the different parts of speech give rise to a number of interpretations, which increases the number of possible translations. Naturally, therefore, the time required for the translation process increases.

Therefore, as shown in FIG. 8, the number of parts of speech that each word constituting the - sentence has may be checked, and the translation processing time may be set based on the total number of parts of speech.

That is, the data t indicating the number of combinations of parts of speech is initialized to (1) (step l), and the number n of parts of speech that each word has from the first 111 words to the last word of the sentence is sequentially checked (step j, k). Then, the calculation t=tXn is performed according to the number n of parts of speech (step J2), and the total number of combinations of the parts of speech is determined as t. This data t is multiplied by the unit time of the translation process to set the time limit T for the translation process of the - sentence (step m).

Specifically, for example, N saw a girl in the park,
When the original text J is input, a search in the translation dictionary 5 first determines that the part of speech for word (1) is (noun;
Since there is only one type of data t, t=(t;1)X(n;1)=(1) can be obtained by stepno processing. For the next word (SaW,), there are three parts of speech: ■see (verb; past of seeing) ■saν (noun; saw) ■saw (verb; past of sawing). Through the processing, t=(t;1)X(n;3)=(3) is obtained. And for the next tli word (girl'l) (
Since there is only one type of noun; girl), t − (t;
3)X(n;1)=(3). Similarly, for the last 11i word (+)ark), (noun; park)
Since there are two parts of speech:

As a result, the above human power original text! (If t = (6) is obtained as the part-of-speech combination data that indicates the external aspect, and the translation processing unit time is set to, for example, 10 seconds, the translation processing time for the original text can be set as 60 seconds. It becomes possible.

In this way, 7. A limit is set on the translation processing time according to the number of words and parts of speech), and if the translation processing is not completed within the time limit, the translation processing mode is switched to, for example, partial translation processing. According to this, it is no longer necessary to spend an unnecessarily long time on translation processing. In addition, it is possible to limit the translation processing time according to the Fu coarseness of the input original text, and to proceed with the translation processing efficiently.

This eliminates the problem of having to translate short and simple sentences over a long period of time. Furthermore, for long and complex sentences, the problem of not being able to obtain correct translation results because the set time is too short is avoided.

If a result is not obtained within the processing time corresponding to the human-powered original text, it is possible to change the translation processing format at an appropriate timing indicated by the set time and proceed with the translation process for the human-powered original text. Become. Therefore, it is possible to significantly reduce the response waiting time from inputting the original text to obtaining the translated result, making it possible to carry out interactive translation processing efficiently.At the same time, the responsiveness can be improved. Therefore, great practical effects such as being able to reduce the psychological and physical burden on the operator can be achieved.

Note that the present invention is not limited to the embodiments described above. Although translation from English to Japanese has been described here, translation may be performed in the opposite direction, and the present invention can be similarly applied to translation processing between other languages. Further, the translation process prepared in the translation unit may be, for example, a form in which the number of part-of-speech sequence candidates tried for a - sentence is limited and the translation process is performed. Further, the translation processing time may be set in consideration of the structural complexity of the human original text.

In addition, the present invention can be implemented with various modifications without departing from the gist thereof.

[Brief explanation of drawings]

The figures show a device according to an embodiment of the present invention. FIG. 1 is a schematic configuration diagram of the device, FIG. 2 is a diagram showing an example of the configuration of the human power section, and FIG. 3 is an example of the configuration of the display screen. 4 is a diagram showing the basic operation sequence of the embodiment device, FIG. 5 is a diagram showing the processing procedure of translation processing, FIG. 6 is a diagram showing an example of the configuration of the translation section, and FIGS. FIG. 8 is a diagram showing the procedure for setting the translation processing time. 1... Input section, 2... Original text storage section, 3... Edit control section, 4... Translation section, 4a... Time setting section, 41)
... Translation processing section, 4c... Elapsed time measuring section, 4d.
...Original text division processing unit, 5...Translation dictionary, 6...Translation storage unit, 7...Display control unit, 8...Display unit, 9...
・Printing department.

Claims (3)

[Claims] (1) A translation dictionary section that stores knowledge information used for translation processing, a translation section that uses the knowledge information to translate the original text given from the input section, and a translation output that outputs the translation obtained by this translation section. a means for measuring the elapsed execution time of the translation process for the input original text; a means for setting the time that can be spent on the translation process according to the input original text; When the set time is reached,
A machine translation device comprising: means for changing the content of translation processing for the input original text. (2) The machine translation device according to claim 1, wherein the time that can be spent on translation processing is set according to the number of words forming the input original text. (3) The machine translation device according to claim 1, wherein the time that can be spent on translation processing is set according to the total number of parts of speech of each word forming the input original text.