JPS62203274A - Mechanical translation system - Google Patents

Abstract

PURPOSE:To attain editing in the unit of sentence by providing a means for instructing the editing in the unit of sentence such as sentence insrrtion/division/ connection/deletion to sentences translated in the unit of sentence. CONSTITUTION:The following keys are provided to edit sentences in the unit of sentence; A paragraph key 120 is used to indicate a paragraph, a sentence deletion key 121 is used to delete a sentence on which a cursor falls, a sentence insertion key 122 is used to insert a new sentence to a position of the cursor, a sentence connection key 123 is used to combine two sentences, a sentence division key 124 is used to divide one sentence into two and a sentence call key 125 is used to call a desired sentence. When an edition key is keyed in, an editing control section 4 detects it and applies the editing processing corresponding to each key to a word or a phrase indicated by the cursor. Then the operator obtains a translated sentence interactively while applying the input of original and the edition of the translated sentence properly.

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 divides the input original text into predetermined processing units such as edicts (phrases) by morphologically and syntactically analyzing it, and then searches a translation dictionary for each processing unit to find the corresponding translation. (Translation: Shun)
etc., and combine them according to predetermined translation rules to obtain the translated text.

However, it is extremely difficult to reliably obtain appropriate translations, partly because the technology for interpreting the meaning of natural expressions has not yet been fully established.

For this reason, in the past, multiple translation candidates obtained as a result of translation were presented to the user, and the translation candidate selected and designated by the user as the most appropriate was output.
There remains a need for the user (operator) to re-edit the translation into an appropriate translation.

Furthermore, the original text to be translated may be extracted at an appropriate position, and the text may be incorrectly recognized without being translated.

[Purpose of the invention]

An object of the present invention is to provide a machine translation system that allows easy editing operations by an operator.

Another object of the present invention is to provide a machine translation system that allows editing on a sentence-by-sentence basis.

[Summary of the invention]

The present invention is characterized in that the machine translation system includes means for instructing sentence-by-sentence editing, such as sentence insertion, sentence division, sentence connection, and sentence deletion, for sentences translated in sentence units. In this case, a new sentence number will not be issued at the time of translation, and the inserted sentences will have 1 inserted in the identification number, the divided sentences will be divided into 5, and the sentences that have been deleted or connected will have no sentences left. By using an identification number such as ``1 Delete'', it is clearly indicated to the operator, and in the case of a statement call, by ignoring sentences with 1 Insert'', 1 Divide, etc. attached to the identification number,
The target sentence can be recalled by specifying the sentence number issued during translation.

Furthermore, the present invention allows paragraphs (paragrams) to be specified or canceled on a sentence-by-sentence basis.

〔Effect of the invention〕

According to this invention, editing of a translated sentence can be performed on a sentence-by-sentence basis without affecting the sentence number issued at the time of translation, so when calling another sentence for editing processing, the translated sentence number can be used. I can do it.

Furthermore, since paragraph designation or cancellation can be easily performed for each translated sentence, the translated sentences can be output in a formatted format that matches the original text.

Therefore, even if a sentence is extracted incorrectly, it can be easily corrected or changed and an appropriate translation result can be easily obtained.

[Embodiments of the invention]

FIG. 1 is an overall block diagram of an English-Japanese machine translation system as an embodiment of the present invention. This system consists of an input unit 1 consisting of a keyboard, an original text storage unit 2 that stores the input English text as the original text, a translation storage unit 3 that stores the Japanese text corresponding to the input English text as the translated text, and controls the entire system. an editing control unit 4 that executes the translation process; a translation unit 5 that executes the translation process;
A translation dictionary 6 that stores knowledge information used in translation processing, a display control unit 7 that controls the display of original texts, translated texts, etc., and a display unit 8
and a printing unit 9 for correcting the original text, translated text, etc. and outputting it as a hard copy.

FIG. 2 is a diagram showing an example of the key arrangement of the input section 1. As shown in FIG.

The input unit 1 is equipped with the following various keys in addition to character keys for English writing.

Translation instruction key=100 Edit key: 101-105 Function key: 110-114 Cursor key: 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 is displayed in the original text display area on the left side of the screen. The translated text obtained as a result of the translation process 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 S4, and the process corresponding to the editing key is performed in step S11.

When the operator operates the cursor key 130 or its corresponding control key, processing for moving the cursor corresponding to the key operation and other processing are performed in step 813 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 then the corresponding character code is sequentially set in the input buffer (not shown) in the editing control unit 4 (step S8). ). 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 5I (1). If input editing such as correction, insertion, deletion, etc. is required during the original text processing, use the cursor keys to move the cursor to the desired editing location. After that, insert key 101, delete key 10
This can be done using the 2nd etc. edit key.

FIG. 5 is a flowchart showing the flow of translation processing in the translation section 5. The translation unit 5 first searches the regular/irregular conversion dictionary 6a for the input original text, and converts words with changes in the 8n tail etc. into their original forms (basic forms).

Next, the translation unit 5 first performs morphological analysis processing on the human original text using the regular/irregular conversion dictionary 6a (step 521
). Since the translation dictionary 6b stores information such as a translation 8n corresponding to each word and its part of speech, information such as its translation and part of speech is obtained for each word constituting the input original sentence. In step 323, the translation unit 5 uses the above information to find grammatically valid translation candidates. In determining this translation candidate, in order to eliminate sequences that form combinations of unconnectable part-of-speech sequences among all combinations of translation words for each word found in step 322, the unconnectable part-of-speech sequence rule dictionary 6G is used. Using this method, only a series of grammatically correct translations 8H are selected as translation candidates. Then, in step 324, the translation unit 5 analyzes the syntax of each translation candidate. That is,
The dictionary 6d is checked for translation dependency, and if each translation word in each translation candidate has modification candidates or polysemous word candidates, these are added as auxiliary information. When the above processing is completed,
The translation section 5 outputs a translation completion signal to the editing control section 4.

Referring again to FIG. 4, when the editing control section 4 detects the translation completion signal in step S1, the process proceeds to step S7, where it sends the translation candidate and auxiliary information obtained from the translation section 5 to the display control section 7 and causes the translation to be displayed. (Step 37). 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 edict or phrase indicated by the cursor at this time (step 511).

For example, by operating the insert key 101, 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 keys 101. 10
Nullifies the effect of 2゜103.

Modifications can be made using the auxiliary information by operating the key 105.
Other dependencies of the word/phrase pointed to by the cursor display candidates.

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 a word in the original text.

By operating the dictionary registration key 112, new words and phrases can be registered.

By operating the dictionary deletion key 113, imperial edicts and phrases registered through dictionary registration can be deleted.

By operating the partial translation key 114, when translation fails, the partial translation is displayed.

Further, the cursor keys include cursor movement keys 130 for moving the cursor in each direction, a unit switching key 131 for switching the unit in which the cursor moves, and an inter-area movement key 132 for moving the cursor between display areas.
, and enlargement/reduction keys for reducing the cursor size character by character or word by word.

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, the following keys are further provided for editing in units of sentences.

The paragraph key 120 is used to indicate a paragraph.

The sentence deletion key 121 is used to delete the sentence where the cursor is located.

The sentence insertion key 122 is used to insert a new sentence at the cursor position.

The sentence connection key 123 is used to connect two sentences.

The sentence division key 124 is used to divide one sentence into two.

A sentence call key 125 is used to call a desired sentence.

FIG. 6 is a flowchart for performing processing corresponding to these sentence unit editing keys.

The sentence-by-sentence editing process will be explained using display examples shown in FIGS. 6 and 7 through ω.

Step S21 detects when the operator instructs a paragraph. Paragraphs are extracted from the original text to be translated according to certain rules, but the operator can also specify new paragraphs based on the readability of the translated text.

For example, in FIG. 7 (indicated by the symbol 200 of υ, (1) indicates a paragraph, and the next 2) indicates that no paragraph is specified. In step 335, for example, the paragraph key 120 is pressed. When a paragraph is already displayed, the paragraph designation is canceled, and if the sentence does not have a paragraph designation, a paragraph identification symbol is set. Sentence 3 in Figure 7 ■ When a paragraph is specified with , the display is changed as shown in (3) shown by reference numeral 201 in "■" in FIG. 7, and the operator is notified.

Step 322 detects when the operator requests deletion of an unnecessary sentence using the sentence deletion key 121. In the embodiment, when editing, the file is not deleted, but a symbol indicating that the sentence number identification symbol 121 has been deleted is set, for example, as shown by the symbol 210 in FIG. In step 334), if all sentences are deleted at the time of saving, in case of mistaken deletion, for example, when re-translating, the original sentence number may be restored.

In step 323, it is detected that insertion of a sentence has been instructed by the sentence division key 124, and in step 833, as shown in FIG.
An insertion area is created as indicated by the reference numeral 220.

Step 824 specifies the position to divide with the cursor,
A division instruction by the sentence division key 124 is detected, and step S
At step 30, the sentence is divided. A divided sentence is indicated by 〉, indicating that the sentence is a divided sentence.

In step 826, it is detected that the operator has pressed the statement recall key 125, and in step S27, the statement number to be recalled is input. For example, when calling the sentence (3) in Figure 7 (■), the number 3 may be input. Similarly in FIG. 7 (■), if 3 is inputted, sentence number 3 will be displayed as the first sentence. Generally, it can be used when you want to display a sentence that is not on the display screen.

In FIG. 7 (2), since it is <inserted>, the actual physical number is 4, but this conversion is performed in step 328. For example, by preparing a table that stores the locations of sentences that have been increased due to insertion, division, etc., it is possible to easily determine whether there is a palindrome that has increased up to the designated sentence number. By displaying the physical sentence number converted in step 328 in step 329, even if editing is performed in units of sentences, the sentence can be called using the translated sentence number.

As a result, for example, if you perform a translation using batch translation, correct red lines in the printed result, and then call up the red-corrected sentences using interactive translation, the effect will not be affected by the edits made on a sentence-by-sentence basis. It is possible to build a machine translation system that does not require any heat.

[Brief explanation of drawings]

FIG. 1 is an overall block diagram of an embodiment of the present invention, FIG. 2 is a diagram showing a key arrangement of an 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. FIG. 5 is a flowchart showing an example of the flow of translation processing used in one embodiment of the present invention, and FIG. 6 is a flowchart showing an example of editing processing for each sentence among the processing of the editing control unit used in one embodiment of the present invention. , FIG. 7 is a diagram showing an example of a display screen for explaining editing processing in units of sentences. 1: Input part 2: Original text storage part 3: Translation text storage part 4: Edit control part 5: Translation part 6: Translation dictionary 8: Display part 9: Print part 120: Paragraph key 121: Sentence deletion key 122: Sentence insertion key 123 : Sentence connection key 124 : Sentence division key
125: Sentence call key Figure 4 (Start) Figure 5
(7th 〈, IV7 people〉 entered 220th 7th (2nd figure)

Claims (6)

[Claims] (1) An input unit having at least character keys and editing instruction means, an original text storage unit that stores the original text to be translated that is input from this input unit, and a translation dictionary unit that stores knowledge information used in translation processing. a translation unit that executes translation processing of the input original text using the contents of the translation dictionary unit; a translation storage unit that stores the translated text obtained as a result of the translation processing; and a translation unit that displays the original text and the translated text. a display section, and a translation editing section for controlling these and for editing the original text or translated text displayed on the display section according to instructions from the editing instruction means, and the input section is configured to perform sentence-by-sentence processing. 1. A machine translation system comprising: a sentence-by-sentence editing instruction means for instructing editing, and the translation editing unit executes editing such as insertion or deletion on a sentence-by-sentence basis in response to the means. (2) The machine translation system according to claim 1, wherein the sentence unit editing instruction means includes paragraph instruction means for specifying a paragraph. (3) The machine translation system according to claim 1, wherein the sentence unit editing instruction means includes sentence deletion instruction means for instructing a sentence to be deleted. (4) The machine translation system according to claim 1, wherein the sentence unit edit instruction means includes sentence insertion instruction means for inserting a new sentence. (5) The machine translation system according to claim 1, wherein the sentence unit editing instruction means includes sentence division instruction means for dividing the displayed sentence. (6) The machine translation system according to claim 1, wherein the sentence unit edit instruction means includes sentence call instruction means for calling a desired sentence.