JPH0442706B2 - - Google Patents

Description

[Detailed Description of the Invention] [Technical Field of the Invention] The present invention efficiently corrects an input original text,
The present invention relates to a machine translation device that can improve the efficiency of translation processing.

[Technical background of the invention and its problems]

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

This type of machine translation device basically performs morphological analysis, syntactic analysis, and semantic analysis of the input original text, classifies the input original text into predetermined language processing units, such as words (phrases), and performs translation processing. The translation dictionary that stores the necessary knowledge information is referred to, and the translated words (translated phrases) are obtained for each language processing unit, and these translated words (translated phrases) are combined according to predetermined translation rules to create a translated sentence for the original sentence. It is configured to generate .

By the way, in order to improve the efficiency of translation processing, it has been considered that, for example, while inputting a character string from a keyboard, the input original text constituted by the character string is successively translated.

That is, when an English sentence is input as the original text, each character string separated by spaces is cut out as a word unit, and the words are sequentially searched in a dictionary. Then, the point in time when a delimiter such as a period is inputted is detected as the completion of inputting a sentence, and the translation process is performed according to the dictionary search results for each word composing the sentence.

However, when inputting the original text in this way,
Strings are not distorted by typos. When you make a mistake in inputting a character string like this, you can usually correct the input string by instructing the cursor to move back to the character position where the input mistake occurred, and then re-entering the characters from that character position. It will be done.

However, in the above-mentioned translation process, by operating the space key, character strings delimited by spaces are determined as word units, and dictionary searches for the characters are sequentially performed. For this reason, a problem arose in that once the space key was operated, the character string input up to that point could not be easily corrected.

[Purpose of the invention]

The present invention has been made in consideration of these circumstances, and its purpose is to make corrections to the input string even when inputting a string and translating the input original text composed of the input string. An object of the present invention is to provide a machine translation device that can easily perform the following operations and improve the efficiency of the present invention.

[Summary of the invention]

The present invention detects the delimitation of a character string given from an input section by inputting a space or a delimiter, for example, and determines the unit of words that becomes a translation unit, and according to the determination result, knowledge stored in a translation dictionary is stored. In a machine translation device that uses information to translate the input character string and obtain its translation, there are character strings that are determined as word units due to a successful dictionary search, and character strings that are determined as a word unit due to a successful dictionary search, and those that are determined as a word unit due to a successful dictionary search, and those that are determined as a word unit due to a successful dictionary search, and those that are determined as a word unit due to a successful dictionary search, and those that are determined as a word unit due to a successful dictionary search, and those that are determined as a word unit due to a successful dictionary search. The part of the string in which the word unit is undetermined due to non-detection is displayed separately, and when cursor back is instructed for a character string in which the word unit is determined, the cursor is moved back to the specified position. When cursor back is instructed for a part of a character string whose word unit is undefined, the cursor is moved back to the indicated position while erasing the character immediately before the cursor position, and characters can also be input from that cursor position. It is characterized by making it possible.

In other words, the character string portions that have been determined as translation processing units and the undetermined character string portions are identified and displayed using, for example, a cursor or brightness modulation, and character strings that can be corrected are clearly indicated. This makes the correction work easier.

〔Effect of the invention〕

Thus, according to the present invention, there are character string parts for which a dictionary search has been performed for which word units have been determined for an input character string, and character string parts that have been determined as word units because a delimiter is not detected or the dictionary search has failed. Since the character string portions that have not been edited are identified and displayed, it is possible to clearly grasp which character strings in the input character string can be modified, and to efficiently perform the modification. Moreover, because a character string whose word unit has not been determined due to a dictionary search failure is displayed separately from others, it is effective to know that there is a possibility that there is an input error in that character string part from the display format. is shown.

Therefore, there are great practical effects, such as making it easier to correct errors in inputting character strings and making it possible to improve the efficiency of the translation process as a whole.

[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, reference numeral 1 denotes an input section consisting of a keyboard and the like. English sentences made up of character strings and the like input through the input unit 1 are sequentially stored in the original text storage unit 2 as original texts to be subjected to translation processing.

The translation unit 4, under the control of the editing control unit 3, creates a translation dictionary 5 in which knowledge information necessary for translation processing is stored in advance.
With reference to , the original text stored in the original text storage section 2 is subjected to machine translation processing in a predetermined processing unit. The translated text obtained by this translation section 4 (Japanese here)
is managed and stored in the translation storage unit 6 in association with the obtained original text.

The knowledge information stored in the translation dictionary 5 is as follows:
For example, regular/irregular change dictionary 5a, word (translation)
It consists of a dictionary 5b, an analysis grammar 5c, a conversion grammar 5d, a generative grammar 5e, and a morpheme generative grammar 5f.

The editing control section 3 drives the display control section 7 to associate the English sentence (original text) stored in the original text storage section 2 and the Japanese sentence (translation text) stored in the translation storage section 6 with each other. , is displayed on a display unit 8 consisting of a CRT display or the like. By displaying the original text and the translated text on the display unit 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 key 1b for translation instructions;
Editing key group 1c, function control key group 1d, and cursor control key group 1 for the display section 8
It is configured with e.g.

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

The original text display area 8b is an area for displaying the input 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 configured as described above.

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

The editing control unit 3 includes a control parameter i indicating the number of effective characters in the character string input from the input unit 1;
A control parameter j indicating the length of the character string portion for which the word unit has been determined is initialized, and translation processing for the input character string is started.

That is, the editing control section 3 monitors the translation processing status in the translation section 4 (step A), and when the translation section 4 completes the translation processing for a certain original text, the editing control section 3 monitors the translation processing state in the translation section 4, and when the translation processing section 4 completes the translation processing for a certain original text, the editing control section 3 displays the translated text obtained by the translation processing. The translated text is stored in the translated text storage section 6, and 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 provided 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, the input key information is "translation instruction key"
If so (step C), the editing control section 3 starts the translation process (step G). This translation process proceeds while performing a dictionary search for each break in the input character string each time it is detected, as will be described later.

In this translation process, for example, as shown in FIG.
is analyzed using the rule/irregular change 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 languages expressed in the past tense, progressive tense, and past participle form into the present tense, and converts languages expressed in the comparative and superlative forms into their original forms (languages).

Next, for each original word of the original text that has been morphologically analyzed as described above, information on its translation word and part of speech is obtained using the translation dictionary 5b (Step R). This process is performed using the translation dictionary 5b using the original word as a headword.
This is done by searching for .

Then, under the control according to the above-mentioned parsing grammar 5c (step S), the input original text is parsed (step T). This parsing process is repeated until the parsing of the original text is successful. Through this syntactic analysis, the arrangement structure of the parts of speech of the original language constituting the original sentence, their dependency relationships, the mode of tense, etc. are determined.

Thereafter, the structure of the parsed original sentence is converted into the syntactic structure of a 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, it is determined that there is an error in the above-mentioned syntactic analysis of the original text, and the process of parsing the original text is restarted.

After that, the translation word candidates obtained for each source word of the original text are calculated based on the syntactic structure of the translation text.
The words are rearranged in the order of the words according to the language form of the translated text to obtain translation candidates for the original text (Step V).
This syntax generation process is performed according to the generation grammar 5f described above.

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

Incidentally, when a plurality of translations are required for one original text, it is convenient to display only one of the translations and simultaneously display the existence of other translations.

On the other hand, returning to FIG. 4, if the input key information is a "character key" (step D), the character code indicated by the character key is stored in the input buffer (step H), and the character code is 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 input 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 no key information is input, or if the input 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 input keys 1a of the keyboard, the information of the input 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 input original text is then displayed on the original text display section 8b of the display section 8 (Step I).

When the translation instruction key 1b is operated at any time during character input, translation processing for the input original text stored in the input buffer is started in accordance with the input key information (steps C and G).

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

In addition, if it is necessary to modify the input original text, while inputting the original text by operating the character input key group 1a,
For example, the editing process is performed by operating the cursor control key group 1e to move the cursor to the corrected part and operating the editing key group 1c for correction, insertion, deletion, etc. Further, by operating the modification key, modification candidates other than the word or phrase indicated by the cursor are displayed using auxiliary information, for example.

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

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

By the way, when inputting a character string from the input unit 1 and translating an original text composed of the input character string, the translation unit 4
performs the following control. FIG. 6 shows the procedure for controlling the display of input characters shown in step I mentioned above.

That is, when character data is input in order from the input section 1, it is determined whether the input character data is a space or not.
Or it is determined whether it is a delimiter (steps a, b). If the input character data is a space or a delimiter, the character string input up to the point in time when the character data is input is cut out as a word string, which is a unit of translation processing, and the string is searched in a dictionary as a headword. (Step c).

Then, it is determined whether the dictionary search was successful or not (step d). If the dictionary search was successful, the character string extracted as described above is determined as one word unit. When determining this word unit, the control parameter j is updated as j←j+i+1 (step e), and then the control parameter i is reset (step f). Then, the determined j character strings in word units are normally displayed on the display section 8 (step g).

On the other hand, if the input character data is not a space or a delimiter, the control parameter i is incremented (step h), and the input character is stored in the i-th character of the temporary buffer TMP (step i). Then, after the final character position (j-th character) of the character string that has been stored as a word unit, the input character stored in the temporary buffer TMP is displayed, for example, inverted.

This storage of character data in the temporary buffer TMP is also performed for character strings that have been extracted as word units by the detection of spaces and delimiters, and have been searched in a dictionary, but for which the dictionary search has failed. . Therefore, a string whose dictionary search fails is
It will not be confirmed as a word unit, and will be displayed in reverse video.

The character strings inputted sequentially from the input unit 1 in this way are displayed in reverse video until they are cut out as a word unit, and then searched in a dictionary after being cut out as a word unit, and when the dictionary search is successful, the character string is displayed in the normal display form. will be changed to.

On the other hand, if an input error or the like is found in the input character string displayed in this manner, correction processing is performed by operating an editing function key or the like.

This correction process is performed by sequentially returning the cursor indicating the next character input position to the highlighted character string as described above, and re-inputting the character data from the cursor's return position. Realized. FIG. 7 shows the flow of the processing procedure, and FIG. 8 shows a display example of the input original text at that time.

Now, when it is detected that the "backspace key" which instructs cursor back has been operated (step k), the cursor position at that time is first obtained as data K (step l). Then, by comparing this cursor position K with the aforementioned control parameter j indicating the end of the character string determined as a word unit, it is determined whether the cursor back was made to a character string determined as a word unit. ,
Alternatively, it is determined whether the word has been applied to an undefined character string (step m).

If a cursor back is specified for a character string that has been determined as a word, it is unnecessary to modify the input string, and the cursor back is assumed to be specified for another purpose. is moved back by one character (step n) and waits for the next instruction input.

On the other hand, when cursor back is instructed for a highlighted character string that has not been confirmed as a word, the cursor moves back to 1 while erasing the input character immediately before the cursor from the temporary buffer TMP.
The character is moved back (step o). Then, the control parameter i indicating the input character position is decremented (step p), and the number of character strings to be highlighted is reduced by one character.

As a result, for example, as shown in Figure 8a, when inputting the original character string ``Because of the wide ramge'', the user notices an error in the word ``ramge'' and instructs the cursor back to correct it. Then, as shown in Figure b, the highlighted characters are erased one by one,
The cursor will be returned to the desired character position.

Thereafter, when correct character data "range" is input, the input character string is successively corrected as shown in FIG. Then, as shown in Figure 8d, input a comma "," to indicate the delimiter, and when it is determined that the dictionary search for the input character string is successful, it is determined as a word unit and the reverse display changes to the normal display. Can be switched.

By instructing the cursor to move back to the character string highlighted in this way, input characters can be easily corrected.

By the way, as mentioned above, it is not possible to confirm a character string that has an input error as a word unit, but the same can be done when a word that is not registered in the translation dictionary, such as a proper noun, is entered. It is no longer confirmed as a word unit. Therefore, there is a possibility that all the character strings input after the character string "tha" which has not been determined as a word unit will become undetermined, as shown in FIG. 8e, for example.

In such a case, the cursor is returned to the word position using cursor back, and if there is an error in the input character string, the character is corrected. Then, the operator instructs that the input character string is correct by operating the "confirmation key".

When the confirmation key is operated to indicate that the word in the first delimiter of the undetermined character string is correct (step R), the character string composing that word and the delimiter indicating the delimiter between the words are displayed. The length L of the character string including the characters is detected (step s). Then, this character string of length L is deleted from the temporary buffer TMP, and the remaining character string is placed in front (step t).

Then, the control parameters i and j are updated as i←i−L and j←j+L (steps u, v), and it is checked whether any character strings still remain in the temporary buffer TMP (step w).

If a character string remains in the temporary buffer TMP, the first delimited character string is searched in the dictionary because there is a possibility that the character string can be formed as a word unit (step x). If this dictionary search is successful (step y),
The process from step s described above is repeated to sequentially obtain character strings that are established as word units, and these are sequentially determined as word units.

If there are no more character strings in the temporary buffer TMP, or if the character strings left in the temporary buffer TMP cannot be determined as word units, the above-mentioned step q will process the character strings as word units. For the confirmed character string, change its highlighted display to normal display.

According to such a confirmation instruction for an undetermined character string, as shown in FIG. 8f, it becomes possible to confirm the input character string in word units up to the part of the character string where an input error has occurred.

As explained above, according to this device, input character strings that have been determined as words and input character strings that have not been determined are distinguished and displayed, and the cursor back has a different function for these character strings. Therefore, it is possible to easily modify the input character string. In addition, since the input character string is divided according to the delimiter symbols and identified and displayed according to the confirmation status of each word, it is possible to easily and effectively give instructions for input errors.

Therefore, great practical effects can be achieved, such as making it easier to input the character strings that make up the original text, and overall improving the efficiency of the translation process.

Note that the present invention is not limited to the embodiments described above. Although we have explained the translation from English to Japanese here, it is also possible to translate it in the opposite direction.
Furthermore, the present invention can be similarly applied to translation processing between other languages. Furthermore, here, the unconfirmed input character string is displayed in reverse as a word unit, but the input character string may be displayed with high brightness or with color, for example. In short, it is sufficient to make the display formats different so that character string portions that have been determined as word units and character string portions that have not been determined as word units can be distinguished.

In addition, there are character strings extracted by delimiters that are undefined as a word unit due to a dictionary search failure, and character strings that are undefined as a word unit when no delimiter is detected. It is also possible to identify and display character strings. In addition, the present invention can be implemented with various modifications without departing from the gist thereof.

[Brief explanation of drawings]

The figure shows a device according to an embodiment of the present invention.
The figure is a schematic configuration diagram of the embodiment device, FIG. 2 is a diagram showing an example of the configuration of the input section, FIG. 3 is a diagram showing an example of the configuration of the display screen, and FIG. 4 is a diagram showing the basic operation sequence of the embodiment device. Figure 5 is a diagram showing the processing procedure of translation processing, Figure 6 is a diagram showing the flow of display control of input character strings, Figure 7 is a diagram showing the flow of control for cursor back and confirmation instructions, and Figure 5 is a diagram showing the processing procedure of translation processing. FIG. 8 is a diagram showing an example of a screen display according to the processing state on the display unit. 1... Input section, 2... Original text storage section, 3... Editing control section, 4... Translation section, 5... Translation dictionary, 6...
Translation storage unit, 7...display control unit, 8...display unit,
9...Printing department.

Claims (1)

[Claims] 1. A translation dictionary unit that stores knowledge information used in translation processing, a translation unit that uses the knowledge information to translate an original text given from an input unit, and a translated text obtained by this translation unit. A machine translation device comprising a translation output unit that outputs a translated text, and a translation editing unit that displays the input original text and the translated text and controls editing of the translation, the translation editing unit instructing the delimitation of input character strings. determining means for sequentially determining word units to be translation units; identification display means for identifying and displaying character strings determined as word units and character string portions for which word units are undetermined; and said determining means. When cursor back is specified for a character string whose word unit has been determined by A machine translation device comprising cursor control means for moving a cursor back to a position while erasing a character immediately before the position. 2. The determining means searches a translation dictionary for the character string specified to be separated according to spaces and delimiters in the input character string, and when the dictionary search is successful, determines the character string specified to be separated as a word unit. A machine translation device according to claim 1, characterized in that: