JPH06176060A - Machine translating device - Google Patents

Abstract

PURPOSE:To improve the quality of a translated language by information a user of a fact that an input sentence of a 1st language lacks some parts against the output of a 2nd language when the proper translation is impossible in the 2nd language owing to the ambiguous input sentence of the 1st language. CONSTITUTION:A data processing part 10 incudes a pre-editing part 12, a translating part 15 which translates the received input sentence into a sentence of a 2nd language, a dictionary part 14, and a post-editing part 15 which edits the translated sentence in terms of software. Then a 1st language is supplied to an input part 11 and the input 1st language is pre-edited into a form suitable to the mechanical translation. The pre-edited 1st language is translated into a 2nd language at the part 13 by making reference to the part 14. The 2nd language, i.e., the result of translation is edited at the part 15. Then both 1st and 2nd languages are shown at a display part 16. Furthermore the part 16 informs a user of a fact that the input sentence of the 1st language lacks some parts against the output of the 2nd language when the proper translation of the 2nd language is impossible owing to the ambiguous input sentence of the 1st language. Thus the user is urged to correct the insufficient input sentence of the 1st language.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a machine translation apparatus for performing translation processing in search of higher quality translations.

[0002]

2. Description of the Related Art In recent years, a system for automatically translating an input sentence using a computer has attracted attention. Such a machine translation device basically divides an input sentence into predetermined processing units such as words (phrases) by performing morphological analysis and syntactic analysis, and searches a plurality of translation dictionaries for each processing unit. It is configured to obtain a translated sentence by finding a corresponding translated word or the like and combining them according to a predetermined translated sentence generation rule.

However, when translating between two different languages, even if the expression is commonly used in one language,
When translating it into the other language, the expression may be too vague to be translated correctly. In many conventional machine translation devices, such ambiguous expressions are often directly translated. On the other hand, in order to obtain a natural and higher quality translation as a second language, the user post-edits it into an appropriate translation in post-processing, or pre-edits it as concretely as possible and re-translates it. It is necessary.

[0004]

However, the conventional machine translation device does not have means for informing the user that an inappropriate translation is available, and therefore the translation output by the computer is incorrect. It was often misleading and left uncorrected.

The present invention has been made in order to solve the above-mentioned problems, and when an appropriate translation in the second language cannot be issued because the input sentence in the first language is ambiguous, the conventional method is used. Providing a machine translation device that informs the user that there is a missing part in the input sentence of the first language in order to produce a more natural translation as the second language instead of directly translating it To do.

[0006]

In order to achieve this object, a machine translation apparatus of the present invention has an input unit for inputting a first language and a form suitable for machine translation of the input first language. A pre-editing section for editing, a first dictionary storing parts of speech corresponding to headwords in the first language and translations in the second language, a second dictionary constructed by each user, and technical terms stored A dictionary unit including the third dictionary, a translation unit for translating the first language into a second language using the dictionary unit, and a post-editing unit for editing the second language as a translation result And a display unit for displaying the first language and the second language. More specifically, the display unit is not able to output an appropriate translation in the second language because the input sentence in the first language is ambiguous. If there is not, the user must confirm that the output of the second language has a missing part in the input sentence of the first language. At the news, and a means to encourage the modification.

[0007]

In the present invention having the above-mentioned structure, the first language is input to the input unit, and the input first language is preedited into a form suitable for machine translation, and then the dictionary is referred to by the translation unit. Is translated into the second language, the second language as the translation result is edited in the post-editing section, and the first language and the second language are displayed on the display section. When the input sentence of the first language is ambiguous and the proper translation of the second language cannot be output, the display unit displays that the output of the second language has a portion that is insufficient for the input sentence of the first language. Notify and prompt the user for correction.

[0008]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS An embodiment of the present invention will be described below with reference to the drawings.

Here, an embodiment in which the first language is Japanese and the second language is English will be described.

FIG. 1 is a block diagram functionally showing the hardware configuration of a machine translation apparatus embodying the present invention. As shown in FIG. 1, the machine translation apparatus 1 includes a data processing unit 10 including a computer, a keyboard 11 as an input unit, a CRT 16 as a display unit, a scanning printer 17 as a printing unit, and the like. It consists of

In the data processing unit 10, the pre-editing unit 12 for editing the input sentence input to the input unit 11 into an appropriate form as needed, and receiving the input sentence from the pre-editing unit 12 receive the first sentence. A translation unit 13 for translating into two languages, a dictionary unit 14 stored in a hard disk or an optical disk, a translation unit 1
The post-editing unit 15 for editing the translation result sentence obtained in 3 is realized as software and is incorporated.

FIG. 2 shows a flow chart used for explaining the operation of this embodiment.

First, when a Japanese sentence which is an input sentence, for example, "Pull the front lever to the left." Is input from the input unit 11 (S1), the Japanese sentence is edited by the front editing unit 12 as necessary. After being edited into an appropriate form (S2), it is sent to the translation unit 13. The Japanese sentence sent to the translation unit 13 is morphologically analyzed by referring to the dictionary unit 14 in the morphological analysis unit 13a as shown in FIG. 3, divided into words, and word information or the like is added to each word (S3). ). Further, as shown in FIG. 4, in the syntactic analysis unit 13b, similarly referring to the dictionary unit 14, words are grouped into phrases, and syntactic analysis such as dependency analysis is performed (S4). After that, in the syntax conversion unit 13c, Japanese is converted into an English structure based on the result of the syntax analysis as shown in FIG. 5 (S5). That is, here, each case element of Japanese is associated with an English case element, and transformed into an appropriate English structure.

The sentence converted into the English structure by the conversion unit 13c is delivered to the syntax generation unit 13d. First, the dictionary unit 14 is similarly searched for each word or group of words. Next, the correct syntax is generated as English based on the translation generation rule (S6). Subsequently, the morpheme generating unit 13e performs morpheme generation such as word form change (S7). The English translation generated in this way is freely edited by the post-editing unit 15 (S8), and the display unit 1
6 or output by the printing unit 17 (S
9).

In the system configured as described above, the display method on the display unit 16 and the process up to that point will be described in detail.

In the conventional machine translation device, the "before" portion is analyzed as "before" + "no", and the "of the fr
Often hitting'ont 'or'former'. However, in the case of the example sentence, 'Pull the lever of the front to the
It's ambiguous whether it's left. 'or'Pull the former lever to the left.', and the more natural reason is'the lever in front of ~ ', which is "what is the lever before?" In addition, 'former leve in the case of "Because the quality of the previous lever is poor, I will change to a new lever this time."
You may want to apply a translation like'lever of the front 'in the case of r'or'If the front lever does not move, try moving the rear lever.'
A description such as "front" is necessary to get a clear English.

Therefore, in this embodiment, simply "previous"
If the translation is "the lever in front of ~", the display is devised to notify the user accurately that the part of Japanese corresponding to ~ is missing. In other words, the English translation part corresponding to the missing part of Japanese is displayed in reverse video or with ~ or ***.

FIG. 6 is a flow chart illustrating the process.

First, in the syntax conversion section, just before "former" or "before" + "no" is used in the "before" as in the conventional system.
Then, instead of applying'former ', a flag indicating that the translation called from the rule is applied to "before" rather than the dictionary is added to "before" (S1). Next, when applying a translation to "before", if there is a flag indicating that there is a translation prepared individually by the system side, instead of applying the translation'front 'of the dictionary, the translation prepared by the system side Is referred to (S2). Next, it is determined whether or not there is a word that is modified by "before" (S3). If there is a word to be modified, continue after "in front of" (S4), and if not, continue with ~ to the part corresponding to the missing word and then "i".
n front of ~ 'is output (S5). Therefore,
If "Pull the lever in front of the set button to th."
e left. ', "Pull the front lever to the left."
Is output as'pull the lever in front of ~. '. FIG. 7 shows the contents of the conversion dictionary described in this process.

The present invention is not limited to the above-mentioned embodiment, and other methods of displaying it to the user in an easy-to-understand manner are conceivable. Also, not only "front" but "back" and "rear"
(Later) There are many other ambiguous and inappropriate words in Japanese, such as "near", in the translation of the word itself. By using this example, the inappropriate part can be seen at a glance in the output result, the user can accurately know what to correct in order to produce a higher quality translation, and the user can identify the missing part. It is possible to further improve the quality of translation by inputting into.

[0021]

As is apparent from the above description,
According to the machine translation device of the present invention, an inappropriate portion can be clearly seen in the output result, and it is possible to accurately understand where to correct in order to produce a higher quality translation, and thus the quality of the translated text can be improved. Can be expected.

[Brief description of drawings]

FIG. 1 is a block diagram showing the configuration of a machine translation device to which this embodiment is applied.

FIG. 2 is a flowchart of the entire translation process provided for explaining the operation of the present embodiment.

FIG. 3 is a diagram showing a morpheme generation process used for explaining the operation of the present embodiment.

FIG. 4 is a diagram showing a parsing process used for explaining the operation of the present embodiment.

FIG. 5 is a diagram showing a syntax conversion process used for explaining the operation of the present embodiment.

FIG. 6 is a flowchart of a syntax conversion process used to explain the operation of this embodiment.

FIG. 7 is a diagram showing a conversion dictionary of this embodiment.

[Explanation of Codes] 1 machine translation device 10 data processing unit 11 input unit 12 pre-editing unit 13 translation unit 14 dictionary unit 15 post-editing unit 15a display control unit 16 display unit 17 printing unit

Claims (1)

[Claims] 1. An input unit for inputting a first language, a pre-editing unit for editing the input first language into a form suitable for machine translation, a part of speech corresponding to an entry word of the first language, and a first part. Two
A first dictionary that stores translated words of a language, a second dictionary constructed by each user, a dictionary unit that includes a third dictionary that stores technical terms, and a first dictionary that uses the dictionary unit. Machine translation including a translation unit for translating a language into a second language, a post-editing unit for editing a second language as a translation result, and a display unit for displaying the first language and the second language In the apparatus, when the input sentence of the first language is ambiguous and the appropriate second language translation cannot be output, the display unit displays the output of the second language with a portion where the input sentence of the first language is insufficient. A machine translation device comprising means for notifying that something is present and means for prompting a user to make a correction.