JP2894064B2 - Machine translation equipment - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a machine translation device,
In particular, the present invention relates to a system that can correct a morpheme in an original sentence and retranslate the corrected original sentence, or a machine translation device that can divide a morpheme in the original sentence (that is, specify word segmentation).

[0002]

2. Description of the Related Art In machine translation, there is a case where a system makes a mistake in word separation or a word separation different from that intended by a user. This is particularly likely to occur when translating original texts with many hiragana characters. Therefore, there has been proposed a machine translation device that allows a user to specify a word break when a word break is made in a translation process or before translation. With this machine translator, the original sentence containing the word segmentation information is displayed on the screen, and the user can consciously specify the part to be segmented and then retranslate to obtain the correct translation. Become.

[0003]

However, in such a conventional example, even if a word is cut off, if the morpheme is in hiragana notation, it is often not registered in the dictionary as a heading of hiragana notation. Even if it is registered, it is ambiguous, so it is necessary to change the hiragana notation to kanji notation or to register it in the dictionary with the heading of the hiragana notation in addition to the designation of word separation. In other words, although the user often designates a word segmentation for an original sentence with many hiragana notations, it is an inefficient operation that it is difficult to obtain a correct translated sentence by word segmentation alone.

[0004]

The object of the present invention is to improve the disadvantages of the prior art, and in particular, to use hiragana notation that can be interpreted in an ambiguous manner.
Can translate Japanese original data with
To provide a machine translation apparatus that, and an object of the present invention.

[0005]

According to the present invention, the language is changed to another language.
Japanese original data including Kanji notation and Hiragana notation to translate
Data input section and kanji or katakana table
Headwords and the corresponding hiragana notation
Has a correspondence table defined in advance and
Original text based on the specified word segmentation position and correspondence table
Hiragana notation morphemes in data
Source morphological conversion unit for converting to
Original text data converted by
The original text data and the source text
Translated sentences by translating the sentence part into other languages
A translation processing unit for generating data. Moreover,
The original text morpheme conversion unit is a device that displays the original text data on the screen.
And the word cut position input by the user according to the display
Hiragana table where the word break position is specified based on the position specification
One or more headwords corresponding to the original part of the description on the screen
Function to display and to the user according to the display of this headword
Therefore, the original part of the hiragana notation
And a replacement function.
This aims to achieve the above-mentioned purpose.
You. In the present invention, the kanji or katakana notation
And the hiragana notation corresponding to the headword
It has a correspondence table defined in advance. And Hara
Possibility of misinterpretation in sentence data and high possibility of mistranslation
Display the headword corresponding to the hiragana notation on the screen,
The user specifies whether the original text has the meaning of this headword.
To reduce the variety of meanings in the original text,
The translation process is performed . Also preferred implementation
In the example, the source morpheme conversion unit converts the morpheme into, for example, Hiragana.
In addition to converting notation to Kanji notation,
Translation processing of word break information according to the specified word break position
Section, and the translation processing section refers to this word separation information to
A cutting process may be performed.

[0006]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The present invention will be described below with reference to the drawings according to embodiments. FIG. 1 is a configuration diagram of the present invention, FIG. 2 is a configuration diagram showing a specific example of one embodiment of the present invention, and FIG. FIG. 9 is an explanatory diagram showing a part of a “correspondence table”. In the drawing, reference numeral 11 denotes an input unit, reference numeral 12 denotes a control unit, reference numeral 13 denotes a translation processing unit, reference numeral 14 denotes an original morphological conversion unit, reference numeral 15 denotes an output unit, reference numeral 21 denotes an input unit, reference numeral 22 denotes a control unit, and reference numeral 23 Denotes a translation processing unit, 24 denotes an original sentence morphological conversion unit, and 25 denotes an output unit.

The input unit 11 performs processing for inputting original text data (original text) from a keyboard, for example. The control unit 12 has the following five functions. The original text is read from the input unit 11 and passed to the translation processing unit 13. The original sentence including the word segmentation information is read from the translation processing unit 13 and passed to the original sentence morpheme conversion unit 14. If not translated, the original text is read from the input unit 11 and passed to the original text morpheme conversion unit 14. The corrected original sentence obtained by converting the morpheme in the original sentence is read from the original sentence morpheme conversion unit 14 and passed to the translation processing unit 13. After the translation processing is completed by the translation processing unit 13, the translation data is extracted and passed to the output unit 15.

The translation processing unit 13 translates the original sentence provided from the input unit 11 and the corrected original sentence provided from the original sentence morpheme conversion unit 14, and generates a translated sentence in consideration of the word segmentation designation. The original text morpheme conversion unit 14 displays the original text on the screen when it is not translated and the original text containing the word segmentation information after translation processing, and converts the original text morpheme in Hiragana notation into an appropriate kanji notation according to the specification of the user. In addition to performing a process of converting the original sentence morpheme, information of word segmentation designation is given to the original morpheme. The output unit 15 displays a translated sentence as a translation result of the translation processing unit 13 on, for example, a screen.

Next, the operation of this embodiment will be described with reference to FIGS. Here, Fig. 2 shows that once the original text is translated,
The operation of correcting the original sentence including the word segmentation information in the original sentence morphological conversion unit is shown. The correction by the designation of the user is performed as follows, for example. First, the control unit 22
Reads the original text “Wait until he comes.” From the input unit 21 and passes it to the translation processing unit 23. Further, after the translation processing is completed, the control unit 22 extracts the original sentence including the word segmentation information from the translation processing unit 23 and sends the original sentence to the original sentence morpheme conversion unit 24. The original sentence morpheme conversion unit 24 displays the original sentence including the word segmentation information on the screen, and accepts a user's specification. The original sentence including the word segmentation information is displayed by inserting a space between the segmented morphemes in order to clarify the word segmentation. Therefore, if the translation process breaks the word, such as "he", "ga", "car", "de", and "wait", as shown in Fig. 2, "waiting for him" is displayed.

By the way, the original text "Wait until he comes."
There are two possible interpretations: "Wait until he comes." And "He waits by car." Here, "Wait until he comes." Is adopted, and the operation of converting the morpheme "Kuru" in Hiragana into the morpheme "Kuru" in Kanji is shown. When the user indicates on the screen the morpheme “Kuru” of the hiragana notation in the original text with a mouse or the like, a search is made for a headword that reads “Kuru” in the Hiragana reading in the dictionary, and words that meet the conditions are used as conversion candidates. Is displayed.

Here, as a method of searching for a headword,
Candidates can be easily searched by referring to the correspondence table between the headword and its hiragana notation in the dictionary shown in FIG. From the table of FIG. 3, three types of “coming”, “repeating”, and “excavating” are displayed as candidates. When the user selects an appropriate headword ("come") from the candidates by any operation, the morpheme is automatically converted to kanji notation, and the correction result of the original text is "he comes Wait until. " Further, the morpheme “come” specified by the mouse or the like is designated as a word segmentation. Subsequently, the control unit 22 takes out the corrected original sentence from the original sentence morpheme conversion unit 24 and accepts the word segmentation designation.
Pass to The translation processing unit 23 generates a translated sentence so as to reflect the morpheme converted by the original sentence morphological conversion unit 24 and its word segmentation designation. Finally, the control unit 22 includes a translation processing unit 23
And outputs the translated sentence to the output unit 25.

When "He waits in a car" is adopted, the user designates the morpheme "car" in the original text on the screen. Then, the dictionary shown in FIG. 3 searches the dictionary for a headword that is “car” in hiragana reading, and the word “car” that meets the condition is displayed as a conversion candidate. Subsequent operations are the same as in the case of employing.

[0013]

As described above, according to the present invention, when translating from Japanese to another language, a word-translation designation can be accepted, and a machine translation system that can re-translate the original text after correcting it. As an example of a search method for the morphemes in the hiragana notation in the original text, by referring to the correspondence table between the headword in the dictionary and the hiragana notation, it is used from the candidates of the corresponding kanji notation morpheme. To the appropriate kanji notation selected by the person,
Further, by re-translating the morpheme as being designated as a word segmentation, it is possible to provide an unprecedented excellent machine translation apparatus capable of efficiently obtaining a correct translated sentence.

[Brief description of the drawings]

FIG. 1 is a configuration diagram showing one embodiment of the present invention.

FIG. 2 is an explanatory diagram showing the configuration and operation of one embodiment of the present invention.

FIG. 3 is an explanatory diagram showing a part of a correspondence table between headwords in a dictionary referred to in one embodiment of the present invention and their hiragana notations;

[Explanation of symbols]

 11, 21 Input unit 12, 22 Control unit 13, 23 Translation processing unit 14, 24 Original morphological conversion unit 15, 25 Output unit

Claims (1)

(57) [Claims] 1. Kanji notation and Hiragana to be translated into another language
An input unit into which Japanese original data including notation is input;
Headwords in Kanji or Katakana notation and their headings
A pair whose correspondence with the hiragana notation corresponding to the word is predefined
And a predetermined word segmentation position designation
Hiragana in the original text data based on the correspondence table
Original form that converts morphological notation into morpheme such as Kanji notation
Element conversion unit and the original text morpheme conversion unit
Modified original data or original data input to the input unit
At the same time as the original sentence part
Generate translation data by translating into other languages
A translation processing unit, wherein the original morphological conversion unit
A function to display the text data on the screen,
Based on the word break position specified by the user
Corresponds to the original part of the hiragana notation with the specified word segmentation position
A device for displaying one or more of the headwords on the screen
Noh and by the user according to the display of this headword
Place the original part of the Hiragana notation in the specified headword
A machine translation device having a function of switching .