JPS6282464A - Machine translation system - Google Patents

Abstract

PURPOSE:To translate fixed-form sentences more properly by storing translated sentences corresponding to fixed-form sentences in a translated word dictionary and outputting the translated sentence corresponding to a fixed-form sentence as it is when this fixed-form sentence is retrieves as the result of dictionary retrieval. CONSTITUTION:Not only general translated words and phrases corresponding to general words and phrases but also translated sentences corresponding to fixed-form sentences (proverbs, idiomatic phrases, idioms, etc.) are stored in a translation dictionary 6. When an original sentence is supplied to a translating part 5 and the start of translation is indicated, the translating part 5 retrieves first a fixed-form sentence dictionary where fixed-form sentences are stored in the translation dictionary 6; and if a fixed- form sentence coinciding with the whole of the sentence is found in the fixed-form sentence dictionary, its Japanese translated sentence is taken out and is outputted as the translation result. If said fixed-form sentence is not found there, normal analysis, conversion, and generating processings are performed to output a translated sentence. Since unnecessary analysis, conversion, and generation processings are not performed if the original sentence coincides a fixed-form sentence, translation is performed with a high quality.

Description

[Detailed description of the invention] [Technical field of invention] This invention relates to improvements in machine translation systems.

[Technical background of the invention and its problems]

In recent years, systems that automatically machine translate input original texts using computers have been attracting attention. This machine translation system basically analyzes the human original text by morphologically and syntactically, divides it into predetermined processing units such as rhymes, and searches a translation dictionary for each processing unit to translate the text. M (Hnn
The system is configured to find translations such as ``Jun'' and combine them according to predetermined translation rules to obtain the translation.

However, for natural language hB, it is extremely difficult to reliably obtain an appropriate translation, partly because the technology for interpreting the meaning has not yet been sufficiently established1.For this reason, conventional methods have been Multiple translation candidates are presented to the user (), and the user selects the most appropriate translation candidate and outputs the specified translation candidate, but the user (operator) still has to re-edit the appropriate translation (). The need remains.

Toriwa (-), when the target of translation is a fixed phrase such as a proverb, idiomatic phrase, or idiomatic phrase, there are many cases in which each imperial sentence is grammatically unsatisfactory, and therefore cannot be translated. Or,
In many cases, a translated sentence that formally satisfies the grammatical overlap and is generated based on the translated phrases for each Shushun ends up being a translated sentence that does not have the meaning of the 4T at all, and in such cases, the operator ends up I had no choice but to translate based on my knowledge.

(Object of the Invention) An object of the invention is to provide a machine translation system in which editing operations by an operator are simple.

Another object of the present invention is to provide a machine translation system that can more appropriately translate a single sentence into a proverb, idiom, idiom, etc.

(Summary of the Invention) This invention is based on the following features: lQ general compatible with Shunshun■
In addition to the words and phrases, the translated sentences corresponding to the fixed phrases are also lost.When the translation department performs a static search and searches for the fixed-19 sentences, it returns to this fixed phrase (each of the sentences that make up the sentence). The interposition of the text omits analysis processing such as analysis, and when generating the translation, the translation corresponding to this fixed phrase can be translated as desired with () and output with the ending and ().

[Efficacy of invention Song Dynasty]

According to this invention, translations corresponding to fixed phrases such as proverbs, idiomatic phrases, and idioms are stored in advance, so that translations can be obtained accurately. In the past, operator-dependent editing processing when a fixed phrase cannot be translated is significantly reduced, and the number of operations 1-9 is greatly reduced. In addition, not only the time required for the editing process but also the time required for the translation generation process of the system is shortened by eliminating the need for part of the analysis process, and the time required to generate the translation as a whole is significantly shortened.

Therefore, it is possible to significantly simplify editing operations and easily obtain appropriate translation results.

[Embodiment of the Invention] FIG. 1 is a block diagram of an English-Japanese machine translation system as an embodiment of the present invention. This system 1.11 includes an input unit 1 consisting of a keyboard, an original text storage unit 2 that stores the manually input English text as the original text, a text storage unit 3 that stores the Japanese text corresponding to the input English text as the translated text, An editing control unit 4 that controls the entire system, a translation unit 5 that executes translation processing, and a translation dictionary 6 that stores knowledge information used in translation processing.
, a display control section 7 that controls the display of the original text, translated text, etc., a display section 8, and a printing section 9 that cleans the original text, translated text, etc. and outputs it as a hard copy.

FIG. 2 is a diagram showing an example of the key layout of the input unit 1.

The human resources section 1 is equipped with various keys below "C" in addition to character keys for English human resources.

Translation instruction key: 100 Edit key: 101-106 Function key: 110-11γ Cursor key 12 130-133 Other keys FIG. 3 is a diagram showing an example of the layout of the screen of the display section 8. The input original text (displayed in the original text display area on the left side of the screen). The sum obtained as a result of the translation process (sentence t: 1°) is displayed in the translated text display area on the right side of the screen at a position corresponding to the original text.

Additionally, the editing area at the top of the screen can be used to display information necessary for various types of editing.

FIG. 4 is a flowchart showing an example of the flow of dialog translation processing by the editing control unit 4. In interactive translation processing, the operator can input the original text and edit the corresponding translated text as appropriate. The editing control unit 4 performs steps 81 to S6.
In this step, it is monitored whether there is any key input from the input unit 1 or whether a translation completion signal is received from the translation unit 5, and if there is any key input, a corresponding process is performed.

If the operator operates any of the function keys, this is detected in step S5, and the process corresponding to that function key is performed in step 312.

When the operator operates any of the editing keys, this is detected in step 84, and processing corresponding to the editing key is performed in step S11.

When the operator operates the cursor key 130ci5 or its corresponding control key, processing for moving the cursor corresponding to the key operation and other processing are performed in step 313 via steps 81 to S6.

When the operator inputs the original text by operating the character keys, each character key is detected in step S3, and the corresponding characters "-" are sequentially set in the input buffer (not shown) in the editing control section 4 ( Step 88). This input original text is displayed in the original text display area of the display section 8 via the display control section 7 (step 89). For example, when the operator finishes inputting a - sentence, the operator presses the translation instruction key 100. This key is detected in step S2, and the editing control unit 4 supplies the original text in the input buffer to the translation unit 5. and instructs the start of translation processing (step 510). In addition, if input editing such as correction, insertion, deletion, etc. is required in the middle of editing the original text, move the cursor to the desired editing location using the cursor keys, and then press the insert key 101 and the delete key 102.
This can be done using editing keys such as .

FIG. 5 is a flowchart showing the flow of translation processing in the translation section 5.

The morphological analysis unit (851) uses the regular/irregular change dictionary 6a to identify words with changes in the ending, etc. of the input original text.
Convert it to its original form (basic form).

In the static search unit (352), the single iE constituting the input original text is
Search for the word Juku8'rIjiju61) for each word, and obtain information such as its part of speech and translation.

The analysis control unit (353) performs a process of sending translation candidates to the syntactic analysis unit.

The syntactic analysis unit (354) uses the analysis grammar 6C to analyze the syntax of the translation candidate and generates an English sentence structure.

If the analysis fails, the process returns to the analysis control section.

The structure conversion unit (S55) converts the English structure into the Nihonyoshi H structure using the conversion grammar 6d. If rejected,
Return to the parser.

The syntax generation unit (356) uses Japanese n according to generative grammar 6e.
The Japanese word order is determined from the structure of n and converted into a word string.

The morpheme generation unit (357) completes the translated sentence by changing the ending of the word using the morpheme generation grammar 6f.

Each of the above-mentioned processing units outputs a signal to the editing control unit 4 at the time of starting processing.

Referring again to FIG. 4, when the m east control section 4 detects the translation completion signal in step S1, the process proceeds to step S7, where it sends the translation candidates and auxiliary information obtained from the translation section 5 to the display control section 7 and displays the translated text. (step 87). The display control unit 7 displays the translation candidate in the translation display area at a position corresponding to the input original text (on the left side of the screen), and if there is auxiliary information, displays the translation with high brightness or in reverse video so that the operator can It is made so that it can be identified.

From this state, when the edit key is pressed, the edit control unit 4
detects this in step S4, and performs editing processing corresponding to each key on the word or season indicated by the cursor at this time (step 511).

For example, by operating the insert key 1 old, a character is inserted before the cursor position. By operating the delete key 102, the character string in the range indicated by the cursor is deleted. By operating the movement key 103, the range indicated by the cursor is moved. By operating the cancel key 104, the above key 101
．． Nullifies the effects of 102.103. By operating the key 105, the modification uses auxiliary information to display other modification candidates for the word or phrase pointed by the cursor.

Note that the following functions can be realized using the function keys.

By operating the translated word display key 110, the translated word can be displayed for each word in the translated sentence. By operating the dictionary display key 111, a dictionary can be displayed for the edict in the original text. By operating the dictionary registration key 112, newspapers and phrases can be registered. By operating the dictionary deletion key 113, words and phrases registered through dictionary registration can be deleted. Partial translation key 1
By performing the operation in step 14, a partial translation is displayed when translation fails.

The cursor keys include a cursor movement key 130 for moving the cursor in each direction, a unit switching key 131 for switching the unit in which the cursor moves, and an area for moving the cursor between display areas. It is comprised of a movement key 132, an enlargement/reduction key for reducing the size of the cursor on a character-by-character basis or on a city-by-city basis, and the like.

Therefore, the operator can interactively obtain a translated text while inputting the original text and editing the translated text as appropriate.

In the system configured as described above, further details of the translation process when the input original text is a fixed text will be explained in detail, taking as an example the case of translating from English to Japanese.

FIG. 6 is a diagram showing the structure of the translation dictionary 6, and FIG. 7 is a flowchart 1 to 1 when translating a fixed phrase.

This will be explained below using FIGS. 6 and 7.

As shown in FIG. 6, the translation dictionary 6 includes 蜆组/irregular change dictionary 6a, KRFr/class 8n dictionary 6b, parsing grammar 6c,
In addition to the conversion grammar 6d, the generation grammar 6e, and the morpheme generation grammar 6f, it has a fixed sentence dictionary 16o.

The fixed phrase dictionary N60 contains English fixed expressions (proverbs, idioms, idioms, etc.) and Japanese 8B translations in pairs. Figure 8 is a diagram showing the structure of the fixed phrase dictionary. In the fixed expression section 8a, English sentences (fixed sentences) are written in - sentences,
The Japanese double translation part 8b contains the Japanese expressions corresponding to each.

When translation starts, before performing the morphological analysis 351, the entire input sentence is searched in the constant q+4 expression section Ba in the fixed phrase dictionary 6g (S71). If there is a phrase in the fixed phrase dictionary whose literary style matches the fixed expression, the crystal translation for that day is taken out (S72). The following steps 851 to 857 are not performed,
The Japanese translation obtained from the fixed phrase dictionary is output as a translation result (S74). If no expression is found in the fixed phrase dictionary, the translated sentence is output (373) through normal processing (851 to $57).

In this way, if you record the translations of standard English sentences as they are in the standard sentence dictionary, unnecessary analysis, conversion, and generation processing will not be performed on the input English sentences registered in the dictionary. It is possible to create a system that can always obtain homogeneous translation results and perform translations of good quality overall.

[Brief explanation of drawings]

FIG. 1 is an overall block diagram of an embodiment of the present invention, and FIG. 2 is a diagram without showing the key arrangement of the input section used in an embodiment of the present invention.
FIG. 3 is a diagram showing an example of the screen layout of the display unit used in an embodiment of the present invention; FIG. 4 is a flow chart showing an example of the processing flow of the editing control unit used in an embodiment of the present invention FIG. 5 is a 7-day chart showing an example of the flow of translation processing used in an embodiment of the present invention, FIG. 6 is a diagram showing the configuration of a translation dictionary, and FIG. 7 is a flowchart when performing fixed phrase processing. FIG. 8 is a diagram showing the structure of a fixed phrase dictionary. 1: Input section 2: Original text storage section 3: Translation storage section 4: Editing control section 5: Translation section 62 Translation dictionary 8: Display section 9: Printing department agent Patent attorney Nori Chika Ken Yudo Take Zai Kikuo (Kaion 0 s!5/ Ward Exit S Zan 7 Ward E Prisoner (helmet)) 1st iz>-, :4.Neishi4ga4苧□q=6(＾
←: Solution 6, ゛ 1 Mu C ← i for town), Mu d ← Grammar for i students: Mu ε 11 world circumference; -; Mu f 5 figure

Claims (1)

[Scope of Claims] An input unit having at least character keys, edit keys, and cursor keys; an original text storage unit that stores an original text to be translated input from the input unit; and a fixed form of knowledge information used for translation processing. a translation dictionary section containing and storing translations corresponding to sentences; a translation section that executes translation processing of the input original text using the contents of the translation dictionary section; and a translation section that stores translations obtained as a result of the translation processing. a storage unit; a display unit for displaying the original text and the translated text; and a display unit for controlling these and for editing the original text or the translated text displayed on the display unit in response to the operation of the editing key or the cursor key, and for displaying the translated text. a translation editing section for controlling a cursor on a display screen of the section, and the translation section translates a translated sentence corresponding to the inputted original text if a fixed phrase corresponding to the inputted original text exists in the translation dictionary section. A machine translation system characterized by producing results.