JP2002183136A - Machine translation system, machine translation processing method, and recording medium recorded with machine translation processing program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To improve the convenience to a user by making it possible to input a word, a phrase, and a control command of a 1st language in voice. SOLUTION: When voice is inputted from a microphone in voice input mode (S31), recognition processing (S32) is performed to discriminate whether the input data are a control command (S33). When so (S33: Y), the processing corresponding to the control command is performed (S34). When it is judged that the input data are a Japanese word or phrase which should be translated (S33: N), its reading data are matched against the index words of a dictionary (S35). When the reading data are found as an index word of the dictionary (S26: Y), it is judged (S37) whether it is necessary to consult a dictionary for the translation and its English equivalent is displayed at a display part (S38) or the dictionary contents are displayed (S39). When the reading data are an unknown word which is not present as an index word (S36: N) and the unknown word data are saved in a RAM as a dictionary registration candidate which is registered in a user dictionary (S40).

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an apparatus for translating an input first language into a second language with reference to a dictionary, and a machine translation apparatus and a machine translation processing method capable of inputting speech. The present invention relates to a recording medium on which a machine translation processing program is recorded.

[0002]

In recent years, various dictionary search software and translation software have been developed in accordance with the improvement of the arithmetic processing capability of computers, and those which are quite useful in assisting human translations have been developed. Have been offered. As such a machine translation device, one using a personal computer system, or a main body of a portable size,
2. Description of the Related Art Portable dedicated machines having a compact display unit and key operation unit have been provided.

[0003] By the way, it is conceivable to use the above-described machine translation apparatus to help the interpreter when, for example, an interpreter who interprets a spoken language comes up with an unknown technical term. However, the above-described conventional machine translation apparatus translates text data input by a key operation or the like, and is not suitable for use in a case where immediacy is required, such as interpretation. Was.

On the other hand, for example, in a personal computer system or the like, the function of voice recognition has also been improved, and some of them have been already realized in which commands are input by voice. Therefore, a configuration in which the above-described machine translation device and the voice recognition function are combined is conceivable.

However, in a simple combination of a machine translation device and a speech recognition function, even if a user attempts to input a command by voice while the translation software is running, the command word is changed to a second language. It is expected that a malfunction such as translation will occur. To avoid this, for example, when inputting the first language to be translated by voice, the translation key may be turned on.
This requires the user to perform a troublesome operation, and the speed of the translation process is inferior to that extent, which is insufficient for improving the convenience for the user.

SUMMARY OF THE INVENTION The present invention has been made in view of the above circumstances, and has as its object to translate an input first language into a second language, and to improve the convenience by enabling voice input. An object of the present invention is to provide a machine translation apparatus, a machine translation processing method, and a recording medium on which a machine translation processing program is recorded.

[0007]

In order to achieve the above object, a machine translation apparatus according to claim 1 of the present invention, a machine translation processing method according to claim 7 and a machine translation processing program according to claim 13 are recorded. The recording medium, when a word or phrase of the first language or a control command for drive control of the device is voice-inputted by the voice input means, determines whether or not the input data is data indicating a word or phrase of the first language to be translated. If the input data is identified as a control command, a process corresponding to the control command is executed, and the input data is identified as a phrase in the first language to be translated. In the case where the first phrase is translated into a second language and output,
Whether to output dictionary contents of words and phrases in the language is set by the output setting means, and when the output setting means sets to translate and output words and phrases in the first language into the second language, When the phrase is translated into a second language with reference to the dictionary and the result is output, and when the output setting means is set to output the dictionary content of the phrase in the first language, the dictionary is referenced with reference to the dictionary. The dictionary contents corresponding to the words in one language are output in the input order by the voice input means. If the words in the first language to be translated are unknown words not in the dictionary, the unknown word data is used as a dictionary registration candidate. It is configured to be stored in the unknown word data storage means.

According to this, it is possible to input the words and control commands of the first language to be translated by voice. At this time, the input data input by voice is converted to the first language to be translated. Whether the data indicates a word or a data indicating a control command is automatically identified, and processing corresponding to the control command is executed, or translation or dictionary lookup is performed. In this case, a word or control command of the first language to be translated is automatically identified, so that quick processing can be performed without forcing the user to perform a troublesome operation for distinguishing them.

When the input data is data indicating a phrase in the first language to be translated, the output setting means sets whether to translate and output to the second language or to output the dictionary contents. Therefore, the user can select either desired output, and it is easy to use and highly convenient. Further, it is conceivable that the word of the first language to be translated is an unknown word that does not exist in the dictionary entry word. In such a case, the unknown word data is stored in the unknown word data storage means as a dictionary registration candidate. , The work of registering the unknown word in the user dictionary later can be easily performed.

[0010] The machine translation apparatus according to claim 2 of the present invention, the machine translation processing method according to claim 8, and the recording medium on which the machine translation processing program according to claim 14 is recorded can be prepared by using a voice input unit to input a word or phrase in a first language. When a control command for drive control of the apparatus is input by voice, the control command indicates whether the input data is data indicating a phrase in the first language to be translated, based on the identification criterion set by the identification setting means. If the input data is identified as a control command, processing corresponding to the control command is executed, and the input data is identified as a phrase in the first language to be translated. In this case, if the phrase in the first language is translated into a second language with reference to the dictionary, the result is output. If the phrase in the first language to be translated is an unknown word not in the dictionary, Having characterized in that the unknown word data is configured to be stored stored in the unknown word data storage means as the dictionary registration candidate.

According to this, it is also possible to speech-input the words and control commands of the first language to be translated. At this time, the speech-inputted input data is converted to the first language to be translated. Whether the data indicates a language phrase or a control command is automatically identified, and processing or translation corresponding to the control command is performed. In this case, a word or control command of the first language to be translated is automatically identified, so that quick processing can be performed without forcing the user to perform a troublesome operation for distinguishing them.

[0012] Since the identification criterion for identifying the input data can be set by the identification setting means, the user can set a desired identification criterion according to, for example, the application. Further, it is conceivable that the word of the first language to be translated is an unknown word that does not exist in the dictionary entry word. In such a case, the unknown word data is stored in the unknown word data storage means as a dictionary registration candidate. , The work of registering the unknown word in the user dictionary later can be easily performed.

According to a third aspect of the present invention, there is provided a machine translation apparatus, a machine translation processing method according to a ninth aspect, and a recording medium on which a machine translation processing program according to the fifteenth aspect is recorded. When a control command for drive control of the apparatus is input by voice, the first language in a specific format set by the identification setting means is used as the control command, and the input data is translated into the first language phrase to be translated. If the input data is identified as a control command, processing corresponding to the control command is executed, and the input data is translated. If a phrase in one language is identified, whether the phrase in the first language is translated into a second language and output or the dictionary content of the phrase in the first language is output When set by the output setting means, and set by the output setting means to translate and output the words and phrases in the first language into the second language, the words and phrases in the first language are referred to a dictionary and converted into the second language. If the translation is performed and the result is output, and if the output setting means is set to output the dictionary content of the phrase in the first language, the dictionary content corresponding to the phrase in the first language is referred to by referring to the dictionary. If the words in the first language to be translated are unknown words that are not in the dictionary, the unknown word data is output and stored in the unknown word data storage means as dictionary registration candidates. It has a feature in the configuration.

[0014] According to this, it is also possible to speech-input words and control commands of the first language to be translated. At this time, the speech-inputted input data is converted to the first language to be translated. Whether the data indicates a language phrase or a control command is automatically identified, and processing or translation corresponding to the control command is performed. In this case, a word or control command of the first language to be translated is automatically identified, so that quick processing can be performed without forcing the user to perform a troublesome operation for distinguishing them.

When the input data is identified, the first language of the specific format set by the identification setting means is used as the control command. It is possible to set an identification standard. At the same time, the first
In the case of data indicating a language phrase, the output setting means can set whether to output by translating to a second language or to output the contents of a dictionary. You can choose,
It is easy to use and highly convenient. Further, it is conceivable that the word of the first language to be translated is an unknown word that does not exist in the dictionary entry word. In such a case, the unknown word data is stored in the unknown word data storage means as a dictionary registration candidate. , The work of registering the unknown word in the user dictionary later can be easily performed.

Further, when the identification criterion is set by the identification setting means, a specific word or a word following the predetermined word can be identified as a control command in the first language input by the voice input means. (Claims 4, 10 and 16). According to this, when identifying the input data, it is possible to more reliably identify whether or not the input command is a control command.

If there is an unknown word, the unknown word may be stored in the unknown word data storage means by pairing the speech data and the translated word data. 17 invention). According to this, unlike the case where the reading data and the translation word data are stored in pairs, it is possible to cope with the habits of the user such as utterance and pronunciation, and to store the unknown word data in a more usable form. Can be.

Further, the translation result and the dictionary content may be displayed on the display means, and at this time, the output content of the translation result and the output content of the dictionary content may be displayed in different forms. According to this, the translation result and the dictionary contents can be output (displayed) to the user in an easily understandable manner while distinguishing them.

[0019]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, a first embodiment of the present invention will be described with reference to FIGS.
In the first embodiment, the present invention is applied to a case where the present invention is realized by a general-purpose personal computer (abbreviated as a personal computer) system. Also, here, the first
An example is shown in which a translation from Japanese as a language to English as a second language is made.

FIG. 2 shows an external configuration of a personal computer system 1 as a machine translation apparatus according to the present embodiment.
, The electrical configuration of the main part is schematically shown by blocks. Here, as shown in FIG. 2, the personal computer system 1 includes, for example, a liquid crystal display on the personal computer main body 2, and includes a Japanese original sentence, a translated English translated sentence, and a control command input as described later. A keyboard 4 and a mouse 5 for inputting various settings, input of original text, instructions of control commands, etc., and a microphone 6 (voice input means). (Hereinafter simply referred to as a microphone 6).

As shown in FIG. 3, a control unit 7 for performing overall control and the like, a hard disk device 8 as an external storage device, a display control unit 9 for controlling the display of the display unit 3, A voice recognition unit 10 for recognizing a voice signal input from the microphone 6, a CD-ROM drive 11
Etc. are provided. The control unit 7 is mainly constituted by a microcomputer, and as is well known, a CPU 12 and a ROM 1
3. A RAM 14 as a memory and an input / output interface 15 are mutually connected by a bus 16.
The input / output interface 15 includes the display control unit 9,
Keyboard 4, mouse 5, voice recognition unit 10, CD-RO
The M drive 11 and the hard disk drive 8 are connected.

The CD-ROM drive 11 is set with a CD-ROM 17 as a recording medium on which a machine translation processing program described later is recorded, and reads the program. The hard disk device 8 stores a dictionary (dictionary data) for translation processing. In this case, this dictionary is configured to include a basic dictionary 18, a specialized dictionary 19 edited for each specialized field, and a user dictionary 20 that the user independently builds.

FIGS. 4A, 4B, and 4C show examples of data structures of the dictionary data, that is, the basic dictionary 18, the specialized dictionary 19, and the user dictionary 20, respectively. These dictionary data include, for example, headword information (reading data) in Japanese, part-of-speech information, translated word information in English, and dictionary information including syntax and semantic information such as fields, inflected forms, usage, and the like. In the translation process, the user dictionary 20 is given the highest priority for the same entry word, and then the dictionary is used (dictionary lookup) in the order of the specialized dictionary 19 and the basic dictionary 18. . The use of the user dictionary 20 and the specialized dictionary 19 depends on the setting of the user.

The control unit 7 controls the CD-RO
By executing the machine translation processing program read from M17, various processes related to translation are executed. More specifically, as will be described later in the description of the operation, a translation process of translating an input Japanese original sentence (input sentence) into English and outputting it (displayed on the display unit 3), an input Japanese phrase Dictionary contents corresponding to (for example, multiple English translations)
Output (displayed on the display unit 3), dictionary output (dictionary lookup) processing, input sentence editing processing for editing the input original text, translation sentence editing processing for editing the translated English translation, A process such as a dictionary editing process for constructing a dictionary is executed.

At this time, in this machine translation process,
A text input mode in which the original text of Japanese is input by text data (character data), a Japanese word to be translated (or dictionary searched), a control command for driving control to be executed (for example, “file”, “file”, ("Help", "Close", "Edit", "Search", etc.) can be executed in a voice input mode in which voice input from the microphone 6 is accepted.

As will be described later in the operation description, in the voice input mode, the control unit 7 controls the input data which is input from the microphone 6 and recognized by the voice recognition unit 10 to be translated into Japanese to be translated. Identifies whether the word is a word or a control command, executes the process if the input data is identified as a control command, and performs the translation process if the input data is identified as a Japanese word to be translated And translate it into English (or look it up in a dictionary) and output it (displayed on the display unit 3). Therefore, the control unit 7 functions as an identification unit, a control command execution unit, a translation unit, and a dictionary content output unit.

At this time, in the present embodiment, a command priority mode, a translation priority mode, and a format designation are used as identification criteria for identifying whether the input data is a Japanese phrase to be translated or a control command. One of the modes,
The mode can be set (selected) by operating the keyboard 4 (or the mouse 5) by the user in advance. Note that the command priority mode is initialized without performing any setting operation. Therefore, the keyboard 4 and the mouse 5 function as identification setting means.

In the command priority mode, whether the input data is a first language (specific phrase) in a specific format,
That is, it is first determined whether or not the command word is "file", "help", or "close". If the command word is any of the command words, it is identified as a control command. Identifies the phrase. The translation priority mode is for identifying all input data as words and phrases in the first language to be translated. Therefore, if a control command is to be executed in this mode, command input by key operation is required. . The format designation mode is for identifying a phrase, which is a specific format, which is input after a predetermined word, as a control command. For example, when a command word is input after a predetermined word "## (sharp sharp)". For example, it is identified as a control command, and if there is no predetermined phrase, it is identified as a phrase in the first language to be translated.

In this embodiment, when the input data is identified as a Japanese phrase to be translated, the translation result is basically output (displayed). By operating the mouse 5) and instructing the output of the dictionary contents, the dictionary contents of the input words in the first language are output. Therefore, the keyboard 4 and the mouse 5 also function as output setting means.

In this case, though not shown, the display unit 3
Is provided with, for example, an area (window) for displaying input data located on the left side, and an area (window) for displaying a translated sentence (translated word) on the right side thereof. This is performed by providing another window so as to overlap with them, so that the translation content and the dictionary content are displayed in different forms. When the dictionary contents are output, the contents are displayed in the order of the input data.

Further, the Japanese phrase input by voice is
When the unknown word does not exist in the dictionary entry, the unknown word data is stored in the RAM 14 as a dictionary registration candidate to be registered in the user dictionary 20. At this time, a data storage file is provided in the RAM 14 so as to function as an unknown word data storage unit.

As a method of voice recognition by the voice recognition unit 10, various known methods can be used. For example, a voice signal input from the microphone 6 is analyzed at predetermined intervals (4 to 20 ms), and a characteristic parameter obtained by extracting a spectrum included in the voice by a band-pass filter bank is stored in a standard stored in a voice recognition dictionary. A method of outputting a standard pattern having a minimum distance as a recognition result as compared with a pattern, a method of using a voiced hidden Markov model, or the like can be adopted.

Next, the operation of the above configuration will be described with reference to FIGS. First, the flowchart of FIG. 5 shows an outline of a translation and editing processing procedure in the text input mode when the control unit 7 executes the machine translation processing program. That is, in step S1,
An original sentence is input in Japanese. This input is performed by the user operating the keyboard 4 to input a Japanese original text, or may be performed by reading an already created original text file. When the Japanese original sentence is input, the input sentence is displayed on the display unit 3 in step S2.

Here, when the user wants to edit the input sentence, the user instructs the editing of the input sentence by the key input operation of the keyboard 4 or the operation of the mouse 5 (step S3).
Yes). Then, in step S4, an input sentence editing process is executed. In the input sentence editing process, edits such as deletion, addition, and correction can be performed on the input sentence displayed on the display unit 3 based on the user's operation of the keyboard 4 and the mouse 5.

In order to translate the input (or edited) original text, the user instructs to edit the input text by operating the keys of the keyboard 4 or the mouse 5 (Yes in step S5). Then, a translation process of translating the input sentence into an English translation is performed (step S6). This translation processing will be described later (FIG. 6). When the translation process is performed, in step S7, the input sentence and the translated sentence are stored in the RAM 14 in an associated state, and in step S8, the input sentence and the translated sentence are displayed on the display unit 3. .

When the user wants to edit the output translation, the user instructs to edit the translation by key input operation of the keyboard 4 or operation of the mouse 5 (Yes in step S9). Then, in step S10,
Editing processing such as deletion, addition, and correction is performed on the translation displayed on the display unit 3. If the user wants to end the translation process, the user performs an end instruction operation (Yes in step S11), and the process ends. For example, when an instruction for another process such as editing of a user dictionary is issued (No in step S11), a process corresponding to the instruction is executed (step S12). Although not shown, it is a matter of course that the input sentence and the translated sentence can be stored in a recording medium such as a floppy (registered trademark) disk or printed as other processing.

FIG. 6 shows the procedure of the above-described translation process (details of the process of step S6 in FIG. 5).
That is, first, in step S21, using a predetermined morphological analysis rule, a dictionary is searched for words constituting an input sentence, words are cut out, and morphological analysis processing for adding search information such as translated words and parts of speech to the morphological analysis results. Is executed. In step S22, based on the result of the morphological analysis process, an analysis process of analyzing the structure of the Japanese language using a predetermined analysis grammar is executed.

In the next step S23, using a predetermined conversion grammar, a conversion process for converting the Japanese structure analyzed by the analysis process into an English structure and replacing individual words with English is executed. Is done. Step S
In step 24, a predetermined generation grammar is used to determine the word order of English from the English structure converted by the conversion process, generate an article specific to English, and supplement the subject necessary for the English sentence. In addition, a generation process of generating an output sentence composed of an English word string is performed by processing a tense, an aspect, a person, a numerical feature, and the like.

In step S25, using a predetermined morpheme generation rule, the English word string generated by the generation process is added to the plural form of the noun, the past of the verb,
The morpheme generation for generating the translated sentence by generating the inflected form such as the past participle is executed, and the translation process is completed.

Now, the flowchart of FIG.
3 shows a processing procedure in the voice input mode during execution of the machine translation processing program by the computer. Here, although not shown, the identification criterion is set in advance (identification setting step), and the command priority mode is set (the setting is not performed by the user and the initial setting is maintained. ).

In the voice input mode, as described above,
Japanese words (words and phrases) to be translated and, for example, "File", "Help", "Close", "Edit",
A control command such as "search" is received by voice input from the microphone 6 (voice input step), and in step S31, a voice input by the user is waited for. If there is a voice input (Yes in step S31),
The input voice is recognized by the voice recognition unit 10 and becomes read data (step S32).

In the next step S33, it is determined whether or not the input data (read data) is a control command, that is, whether or not it is in a command word (identification step). If the input data is identified as a control command (step S33)
In step S34, a process corresponding to the control command is executed (control command execution step).

On the other hand, if it is determined that the input data is not a control command (No in step S33), it is determined that the input data is a Japanese phrase to be translated, and in the next step S35, Matching is performed between the read data and the dictionary entry. If the read data exists in the dictionary entry (Yes in step S36), it is determined in step S37 whether to translate and output or to output the dictionary contents (dictionary lookup).

Here, as described above, if the user does not perform any operation, the translation is performed as it is, and the user performs a key operation to perform dictionary lookup (output setting step). In the case of, step S3
In step 8, the input data is translated, and the result (English translation (translation)) is displayed on the display unit 3 (translation step). If the output of dictionary contents (dictionary lookup) is set, the dictionary contents are displayed on the display unit 3 in the order of input in step S39 (dictionary content output step).

On the other hand, if the input data (reading data) input by voice is an unknown word that does not exist in the headword of the dictionary data (No in step S36), the unknown word is read in step S40. The word reading data is written and stored in the data storage file of the RAM 14 as a dictionary registration candidate (unknown word data storage step). Further, in the present embodiment, even if the input data exists in the entry word of the dictionary data and is translated, the input data (and the translated word data) is set as a dictionary registration candidate in the RAM 14 by a user operation, for example. (Step S41).

Thus, in the voice input mode,
The user can input a Japanese phrase or a control command to be translated into English by voice from the microphone 6. At this time, the data input by voice is a Japanese phrase to be translated. Whether the command is a control command is automatically identified, and translation (dictionary lookup) or command execution is performed.

Therefore, a special operation for discriminating between a word to be translated and a control command is not required, so that the user is not required to perform a troublesome operation and the speed of processing can be improved. Therefore, it is possible to easily and quickly translate Japanese words and phrases, which is suitable for use, for example, when an interpreter translating a spoken language is used to assist an interpreter when unknown technical terms appear. It becomes.

When the input data is data indicating a phrase in the first language to be translated, the user can set whether to translate and output to the second language or to output the contents of the dictionary. Therefore, the user can select either desired output, which is easy to use and highly convenient. At the same time, the user can also set (select) an identification criterion for identifying whether the command is a control command from among the three modes, so that a desired identification criterion can be set.

In this case, a detailed description is omitted, but by inputting a command word followed by a voice input of a predetermined word (for example, “## (sharp sharp)”), a format designation mode for identifying a control command is set. By setting, it is possible to more reliably identify whether the command is a control command or a phrase in the first language to be translated. The user
If it is determined that the control command will not be input by voice, the translation priority mode is set so that all input data can be immediately translated, and the processing time from voice input to output (responsiveness) ) Can be increased.

Further, when the Japanese phrase to be translated is an unknown word which does not exist in the dictionary data entry words, the input data can be stored and saved in the data storage file of the RAM 14 as a dictionary registration candidate. Therefore, when the user later calls the data storage file in the RAM 14, the work of registering the unknown word in the user dictionary 20 can be easily performed.

As described above, according to the present embodiment, the input Japanese language is translated into English, and the voice input is enabled, and the voice input data is translated into Japanese words and phrases. Or a control command is automatically identified, so that the translation of Japanese phrases can be performed easily and quickly, and the convenience for the user can be improved. To play.

Further, in the present embodiment, in particular, when the input data is Japanese to be translated, the user can set whether to translate or to look up in the dictionary, and together with this, it is possible to determine whether or not it is a control command. The user can also set the identification criterion for the translation, which makes it easy to use and convenient. Furthermore, if the Japanese word to be translated is an unknown word that does not exist in the dictionary, the unknown word Since data is stored and saved as dictionary registration candidates, advantages such as easy registration of the user dictionary 20 can be obtained.

FIG. 7 shows an external configuration of a machine translation apparatus 21 according to the second embodiment of the present invention. This machine translator 21 is different from the one using the personal computer system as in the first embodiment, and is a portable dedicated machine that translates the input first language (Japanese) into the second language (English). Is configured as The machine translation device 21 has an LCD for displaying an input Japanese original sentence (input sentence) and an English translation sentence on a surface portion of a main body case 22 having a thin rectangular shape of a portable size. And a key operation unit 24 having a number of keys for the user to perform necessary operations.

The key operation unit 24 includes a number of character input keys 24a for inputting an original text and a return key 2
4b, a menu key 24c for setting functions, a cancel key 24d, a changeover switch 2 as an identification setting means for switching between a command priority mode and a translation priority mode
4e, a dictionary lookup key 24f or the like is provided as output setting means for instructing dictionary lookup. The main body case 22 is connected to a microphone 25 as voice input means, and is connected to, for example, a charging terminal 26 connected to a commercial power supply, and a data for exchanging data with an external device (such as a personal computer). A transmission connector 27 and the like are also provided. If this connector 27 is used, the specialized dictionary 1
It is also possible to preload the data of No. 9 from a personal computer or the like.

Although not shown, the main body case 22 includes a control section mainly composed of a microcomputer for controlling the entire apparatus, various processing circuits for voice recognition processing and data input / output processing, and a power supply. Secondary battery or the like is provided. At this time, a machine translation processing program, dictionary data for translation processing, and the like are stored in a memory (ROM) of the control unit (microcomputer). The RAM of the control unit is provided with a data storage file for storing and storing unknown word data and the like.

In this case, by operating the menu key 24c, as in the first embodiment, a text input mode in which a Japanese original is input by text data (character data), and a Japanese phrase to be translated. It is also possible to execute a voice input mode in which a drive control command to be executed is received by voice input from the microphone 25.

Further, in the voice input mode,
By operating the changeover switch 24e, the mode can be switched between the command priority mode and the translation priority mode. In translation priority mode, microphone 2
5, the translation processing (displaying the words and translations of the original sentence on the display unit 23) is performed assuming that all of the input data that has been voice-inputted and speech-recognized are Japanese words to be translated. Therefore, in order to execute a command in this mode, a command input by the key operation unit 24 is required.

In the command priority mode, as in the first embodiment, the control unit controls the microphone 2
5 to determine whether the input data is a Japanese word to be translated or a control command. If the input data is identified as a control command, the input data is processed. If the data is identified as a Japanese phrase to be translated, it is translated and translated into English and output (displayed on the display unit 23).

At this time, the translation is normally made and the result is output, but when the user turns on the dictionary lookup key 24f, the dictionary contents are output (displayed). Further, when the voice-inputted Japanese phrase is an unknown word that does not exist in the headword of the dictionary data, the unknown word data is stored as a dictionary registration candidate to be registered in the user dictionary in the data storage file of the RAM. It is designed to be stored and saved. Further, the information of the unknown word can be taken into the personal computer through the connector 27.

Therefore, also in the second embodiment,
Similar to the first embodiment, the present invention is for translating input Japanese into English, enabling voice input, and determining whether the input data input by voice is a Japanese phrase to be translated. Since a configuration for automatically identifying whether or not the command is a control command is provided, it is possible to easily and quickly translate Japanese words and phrases, and to achieve excellent effects such as improvement in convenience for the user. . In addition, in the present embodiment, since the apparatus is configured as a portable type, it is possible to obtain an advantage that the apparatus is excellent in portability when interpreting.

In each of the above embodiments, the unknown word is stored in the RAM.
In the storage of the data in the data storage file, the reading data is stored, but the unknown word may be stored in a pair of the voice data and the translated word data. It is possible to cope with habits such as utterance and pronunciation, and it is possible to make the data easier to use. In each of the above embodiments, whether to output the translation result or the dictionary contents is set by a key operation. However, the output setting may be set in advance by mode setting.

The recording medium on which the machine translation processing program is recorded is not limited to the CD-ROM 17, but may be a magnetic disk, semiconductor memory, CD-R, MD, MO, P
Various media such as D, DVD, and magnetic tape can be used. Not only translation from Japanese to English, but also translation from English to Japanese, as well as the first and second languages from all over the world The present invention can be implemented by appropriately changing the scope of the present invention without departing from the gist, such as providing a speech synthesis function to output a translated sentence or a translated word by synthesized speech. What you get.

[0063]

As is apparent from the above description, according to the present invention, it is determined whether the input data voice-input by the voice input means is a phrase in the first language to be translated or a control command. If the input data is identified as a control command, the process is executed. If the input data is identified as a phrase in a first language to be translated, the input data is translated into a second language and output. When the phrase in the first language to be translated is an unknown word that does not exist in the headword of the dictionary data, the unknown word data is stored and stored in the memory as a dictionary registration candidate. And at the same time, it is possible to improve the convenience for the user.

[Brief description of the drawings]

FIG. 1 shows a first embodiment of the present invention, and is a flowchart showing a processing procedure at the time of voice input.

FIG. 2 is a diagram illustrating an appearance of a machine translation apparatus.

FIG. 3 is a block diagram schematically showing an electrical configuration of the machine translation apparatus.

FIG. 4 is a diagram schematically showing a structure of dictionary data.

FIG. 5 is a flowchart showing a translation and editing processing procedure in a text input mode;

FIG. 6 is a flowchart showing a procedure of a translation process;

FIG. 7 is an exemplary perspective view showing the appearance of a machine translation apparatus according to a second embodiment of the present invention;

[Explanation of symbols]

In the drawings, 1 is a personal computer system (machine translation device), 2 is a personal computer body, 3 and 23 are display units (display means), 4 is a keyboard (identification setting means and output setting means), and 6 and 25 are microphones (voices) Input means), 7 is a control unit (identification means, control command execution means, translation means,
Dictionary content output means), 10 is a voice recognition unit, 11 is a CD-
ROM drive, 12 for CPU, 13 for ROM, 14 for RAM (unknown word data storage means), 17 for CD-ROM
(Recording medium), 20 is a user dictionary, 21 is a machine translation device, 22 is a main body case, 24 is a key operation unit, 24e is a changeover switch (identification setting means), and 24f is a dictionary lookup key (output setting means).

Claims (18)

[Claims] 1. A machine translation device for translating an input first language into a second language with reference to a dictionary, wherein a speech of a phrase in the first language or a control command for drive control of the device is input. Input means for identifying, and identification means for identifying whether the input data from the audio input means is data indicating a word or phrase in a first language to be translated or data indicating a control command. When the input data is identified as a control command, a control command executing means for executing a process corresponding to the control command;
Output setting means for setting whether to translate the phrase in the first language into a second language or to output the dictionary content of the phrase in the first language when the phrase is identified as a language phrase; When the output setting means is set to translate and output the words and phrases in the first language into the second language, the words and phrases in the first language are translated into the second language with reference to the dictionary, and the result is obtained. Translating means for outputting; and if the output setting means has set to output a dictionary content of a phrase in the first language, the dictionary content corresponding to the phrase in the first language is referred to by voice input with reference to the dictionary. Dictionary content output means for outputting in the order of input by the means, and unknown word data storage means for storing and storing the unknown word data as dictionary registration candidates when the word in the first language to be translated is an unknown word not in the dictionary. To have Machine translation apparatus according to symptoms. 2. A machine translation apparatus for translating an input first language into a second language with reference to a dictionary, wherein a speech of the first language words or a control command for drive control of the apparatus is inputted. Input means for identifying the first language to be translated or data indicating a control command to be translated, and an identification means for identifying whether the input data is data indicating a control command or not. An identification setting unit that sets an identification criterion for identifying input data input by the input unit; and, if the input data is identified as a control command by the identification unit, the identification command corresponds to the control command. A control command executing means for executing a process, a first command to be translated by the input data,
A translation unit for translating the phrase in the first language into a second language by referring to the dictionary and outputting a result when the language phrase is identified as a phrase in the first language; An unknown word data storage means for storing and storing the unknown word data as a dictionary registration candidate when is an unknown word not present in the dictionary. 3. A machine translation apparatus for translating an input first language into a second language with reference to a dictionary, wherein a speech of a phrase in the first language or a control command for drive control of the apparatus is input. Input means for identifying the input data by the voice input means, and identification means for identifying whether the input data is data indicating a phrase in a first language to be translated or data indicating a control command. Identification setting means for setting the identification means to identify the first language in a specific format as a control command, and when the input data is identified as a control command by the identification means, A control command execution means for executing a process corresponding to the control command, and a first command to translate the input data by the identification means.
Output setting means for setting whether to translate the phrase in the first language into a second language or to output the dictionary content of the phrase in the first language when the phrase is identified as a language phrase; When the output setting means is set to translate and output the words and phrases in the first language into the second language, the words and phrases in the first language are translated into the second language with reference to the dictionary, and the result is obtained. Translating means for outputting; and if the output setting means has set to output a dictionary content of a phrase in the first language, the dictionary content corresponding to the phrase in the first language is referred to by voice input with reference to the dictionary. Dictionary content output means for outputting in the order of input by the means, and unknown word data storage means for storing and storing the unknown word data as dictionary registration candidates when the word in the first language to be translated is an unknown word not in the dictionary. To have Machine translation apparatus according to symptoms. 4. The identification setting means sets an identification criterion such that the identification means identifies a specific word or a word following a predetermined word as a control command in the first language input by the voice input means. The machine translation apparatus according to claim 2 or 3, wherein: 5. The machine translation apparatus according to claim 1, wherein the unknown word data storage unit stores the unknown word in pairs of voice data and translated word data. . 6. A display means for displaying output contents of said translation means and dictionary contents output means, wherein said display means displays output contents of said translation means and output contents of dictionary contents output means in different forms. 6. The method according to claim 1, wherein
A machine translation device according to any one of the above. 7. A machine translation processing method for translating an input first language into a second language by referring to a dictionary by a machine translation device, wherein the speech input means drives the phrase or the device of the first language. A voice input step of receiving a voice input of a control command for control, and a first input data to be translated in the voice input step.
An identification step of identifying whether the input data is data indicating a language phrase or a control command; and, if the input data is identified as a control command in the identification step, a process corresponding to the control command A control command execution step of executing a first command to be translated by the input data in the identification step.
When a language phrase is identified, the output setting means sets whether to translate the first language phrase into a second language and output it or to output the dictionary content of the first language phrase. An output setting step, wherein in the output setting step, when it is set to translate and output the words and phrases in the first language into the second language, the words and phrases in the first language are translated into a second language with reference to the dictionary. A translation step for outputting the result; and a dictionary content corresponding to the phrase in the first language with reference to the dictionary if the output setting step is set to output the dictionary content of the phrase in the first language. And a dictionary content output step of outputting, in the order of input by the voice input means, an unknown word data storage means as a dictionary registration candidate when a word in the first language to be translated is an unknown word not in the dictionary. Memory And storing an existing unknown word data. 8. A machine translation processing method for translating an input first language into a second language with reference to a dictionary by a machine translation device, wherein the speech input means drives the first language phrase or device. A voice input step of receiving a voice input of a control command for control, and a first input data to be translated in the voice input step.
An identification step of identifying whether the data is data indicating a language phrase or a control command; and an identification setting step of setting an identification criterion for identifying input data in the identification step by identification setting means; A control command execution step of executing a process corresponding to the control command when the input data is identified as a control command in the identification step; a first command to be translated by the input data in the identification step;
A translation step of translating the phrase in the first language into a second language by referring to the dictionary and outputting the result if the phrase is identified as a language phrase; If the word is an unknown word not in the dictionary, the unknown word data is stored in the unknown word data storage means as a dictionary registration candidate. 9. A machine translation processing method for translating an input first language into a second language by referring to a dictionary by a machine translation device, wherein the speech input means drives the phrase or the device of the first language. A voice input step of receiving a voice input of a control command for control; a first input data to be translated in the voice input step;
An identification step of identifying whether the data is data indicating a language phrase or a control command;
An identification setting step of setting the language as a control command by the identification setting means so as to be identified in the identification step; and, if the input data is identified as a control command in the identification step, the language corresponds to the control command. A control command execution step of executing processing, and a first step of translating the input data in the identification step.
When a language phrase is identified, the output setting means sets whether to translate the first language phrase into a second language and output it or to output the dictionary content of the first language phrase. An output setting step, wherein in the output setting step, when it is set to translate and output words and phrases in the first language into a second language, the words and phrases in the first language are translated into a second language with reference to the dictionary. A translation step of outputting the result; and a dictionary content corresponding to the phrase in the first language with reference to the dictionary when the output setting step is set to output the dictionary content of the phrase in the first language. A dictionary content output step of outputting the words in the first language to be translated, if the words in the first language to be translated are unknown words not in the dictionary, as unknown dictionary data storage means. In memory Machine translation processing method characterized by including the unknown word data storage step of. 10. In the identification setting step, an identification criterion is set so that a specific word or a word following a predetermined word in the first language input in the voice input step is identified as a control command in the identification step. 10. The machine translation apparatus according to claim 8, wherein the translation is performed. 11. The unknown word data storing step, wherein the unknown word is stored in the unknown word data storage means in a form of a pair of voice data and translated word data. A machine translation processing method according to any one of the above. 12. In the translation step and the dictionary contents output step, the output contents are displayed on a display means, and the output contents of the translation step and the dictionary contents output step are displayed in different forms. Claims 7 to 1
2. The machine translation processing method according to any one of 1. 13. A recording medium storing a machine translation processing program for causing a computer to execute a process of translating an input first language into a second language with reference to a dictionary, wherein the machine translation process is performed. The program causes a voice input means to input a word or phrase of the first language or a control command for drive control of the device, and controls whether the input data by the voice input means is data indicating a word or phrase of the first language to be translated. If the input data is identified as a control command,
Executing a process corresponding to the control command, and when the input data is identified as a phrase in a first language to be translated, translates the phrase in the first language into a second language and outputs or The output setting means sets whether to output the dictionary contents of the words and phrases in the first language, and when the output setting means has set to translate and output the words and phrases in the first language into the second language, the first The language phrase is translated into a second language with reference to the dictionary, and the result is output. If the output setting unit is set to output the dictionary content of the first language phrase, the dictionary is referred to. Then, the contents of the dictionary corresponding to the words in the first language are output in the order of input by the voice input means. If the words in the first language to be translated are unknown words not in the dictionary, the unknown word data is translated into the dictionary. Not a candidate for registration A recording medium storing a machine translation processing program, wherein the program is stored in an intellectual language data storage unit. 14. A recording medium storing a machine translation processing program for causing a computer to execute a process of translating an input first language into a second language with reference to a dictionary, wherein the machine translation process is performed. The program causes a voice input means to input a word or phrase of the first language or a control command for drive control of the device, and controls whether the input data by the voice input means is data indicating a word or phrase of the first language to be translated. If the input data is identified as a control command, it is determined whether the input data is a control command.
A process corresponding to the control command is executed. When the input data is identified as a phrase in a first language to be translated, the phrase in the first language is referred to the dictionary and converted to a second language. Translating and outputting the result; if the word of the first language to be translated is an unknown word that is not in the dictionary, the unknown word data is stored and saved in the unknown word data storage unit as a dictionary registration candidate. Recording medium on which a machine translation processing program is recorded. 15. A recording medium storing a machine translation processing program for causing a computer to execute a process of translating an input first language into a second language with reference to a dictionary, wherein the machine translation process is performed. The program causes a voice input means to input a word or phrase of the first language or a control command for drive control of the device, and controls whether the input data by the voice input means is data indicating a word or phrase of the first language to be translated. The identification data is set to be identified by the identification setting unit so that the identification unit identifies the first language in a specific format input by the voice input unit as a control command. If the input data is identified as a command, a process corresponding to the control command is executed, and the input data is translated into a first language. When the word is identified as a word, the output setting means sets whether to translate and output the word in the first language into a second language or to output the dictionary content of the word in the first language. When the output setting means is set to translate and output the words and phrases in the first language into the second language, the words and phrases in the first language are translated into the second language with reference to the dictionary, and the result is output. If the output setting means sets to output the dictionary content of the first language word, the dictionary content corresponding to the first language word is output in the input order by the voice input means with reference to the dictionary. A machine translation processing program characterized in that, when a word in the first language to be translated is an unknown word not in the dictionary, the unknown word data is stored and stored in the unknown word data storage means as a dictionary registration candidate. Record The recording medium. 16. The machine translation processing program according to claim 1, wherein the identification setting unit determines an identification criterion so as to identify, as a control command, a specific word or a word following a predetermined word in the first language input by the voice input unit. 16. A recording medium on which the machine translation processing program according to claim 14 or 15 is set. 17. The machine translation processing program according to claim 13, wherein the unknown word data is stored and stored in an unknown word data storage unit by pairing the voice data and the translated word data. A recording medium on which the program for processing a machine translation described in 1 above is recorded. 18. The machine translation processing program according to claim 13, wherein the translation result and the dictionary content are displayed on a display means, and the output content of the translation result and the output content of the dictionary content are displayed in different forms. 18. A recording medium recording the machine translation processing program according to any one of 17.