JPH1145245A - Foreign language sentence interpretation support system, storing medium for storing foreign language sentence interpretation support program and method for foreign language sentence interpretation support - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a system for foreign language sentence interpretation support system that can obtain more natural translation results. SOLUTION: At the outset, specific non-translated words and phrases such as compound noun phrase or the like are extracted from a translation object document (in English and so on) by a natural language processing. Then, the whole object document is translated by converting part of non-translated words and phrases to katakana Japanese syllabary transcription without translating the part of non-translated words and phrases word by word. Thus, reading as the whole text of which the contents are known becomes easy by transcribing katakana, for example 'AKUSHON MANEJA' instead of strangely translating 'Action Manager' word by word. Also, since even a user who does not know the contents can read other parts on the assumption that they are written in special words and phrases rather than an obscure verbatim translation, he can go on reading without being confused.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a foreign language reading comprehension support system, a storage medium storing a foreign language reading comprehension support program, and a foreign language reading comprehension support method.
Regarding translation of acquired documents.

[0002]

2. Description of the Related Art A translation system for translating a document (foreign language sentence) created in a predetermined language into a document in a different language, such as a system for translating a document written in a foreign language into a Japanese document, is practical. Has been 2. Description of the Related Art Translation systems have been widely used nowadays when information can be freely and massively obtained through various communications such as the Internet and personal computer communications. In this translation system, an original sentence (translation target document) is translated into a predetermined language according to a predetermined algorithm using a dictionary for translation. Since translation is performed in a relatively short time, it is effective in understanding a homepage created in a foreign language when communicating.

[0003]

However, in a conventional translation system, if a word that does not exist in the dictionary is present in the original sentence, the word is translated verbatim. In some cases, it became impossible to read. This is because, although words such as compound noun phrases, which should originally have meaning as a unit, cannot be accurately recognized, these words are separated and word-for-word translated. For example, as shown in FIG.
er is now varing. So… ”, the conventional translation system uses“ Action M
The word "anager" is translated into "acting section manager" by word-by-word translation. As a result, the translation "The acting section manager is now diversified. So ..."didn't make much sense.

The present invention has been made to solve the above-mentioned conventional problems, and has as its first object to provide a foreign language sentence reading support system capable of obtaining a more natural translation result. . It is a second object of the present invention to provide a storage medium storing a foreign language sentence reading support program capable of obtaining a more natural translation result. It is a third object of the present invention to provide a foreign language sentence reading comprehension method capable of obtaining a more natural translation result.

[0005]

In the foreign language sentence reading support system according to the first aspect, as shown in FIG. 5, a target document acquiring means 501 for acquiring a target document to be translated.
And a non-translated phrase extracting unit 502 for extracting a non-translated phrase from the target document acquired by the target document acquiring unit 501.
A translation dictionary 503; and a translation unit 504 for translating the target document using the translation dictionary 503. The translation unit 504 is configured to translate the non-translated phrase extracted by the non-translated phrase extraction unit 502. The first object is achieved by translating the original notation in the target document as a translation. In the foreign language sentence reading comprehension support system according to claim 2, as shown in FIG. 6, a target document acquisition unit 501 for acquiring a target document to be translated, and a non-translated target document acquired by the target document acquisition unit 501, A non-translated phrase extraction unit 502 for extracting a translated phrase, a notation conversion unit 505 for converting the non-translated phrase extracted by the non-translated phrase extraction unit 502 into a notation by a translation target word, and a translation dictionary 50
And translation means 506 for translating the target document using the translation dictionary 503, wherein the translation means 506
Is the notation converted by the notation conversion means 505 or the notation converted by the notation conversion means 505 and the original text in the target document as the translated word of the non-translated word extracted by the non-translated word extraction means 502. By translating the target document using both notations of the notation, the first
Achieve the objectives. According to the invention described in claim 3, in the foreign language sentence reading comprehension support system described in claim 1 or 2, as shown in FIGS. Extracts noun phrases that do not independently exist as non-translated phrases. According to the invention described in claim 4, as shown in FIGS. 6 and 7, in the foreign language sentence reading comprehension support system described in claim 1 or 2, the non-translated word / phrase extraction means 502 converts the compound noun phrase into Extract as translated words. According to the invention described in claim 5, as shown in an example in FIG. 7, in the foreign language sentence reading support system according to any one of claims 1 to 4, the non-translated phrase The translation means 504 comprising importance determination means 507 for determining importance;
Displays the non-translated phrase in distinction from other translated parts according to the importance determined by the importance determination means 507. In the invention described in claim 6, in the foreign language reading comprehension support system according to any one of claims 1 to 4, as shown in an example in FIG. Search means 5 for searching for a similar document or a related description for at least one unit of a paragraph, a sentence, and a non-translated phrase of the target document acquired by 501
08 and the associating unit 50 for associating the similar document or the related description searched by the searching unit 508 with the corresponding unit.
9 is provided. In the invention described in claim 7, as shown in FIG. 9, a target document acquisition function 601 for acquiring a target document to be translated, and the target document acquisition function 601
A non-translated phrase extraction function 602 for extracting a non-translated phrase from the target document acquired in step 2, a translation dictionary 603, and a translation function 6 for translating the target document using the translation dictionary 603
04, and the translation function 604 is a computer-readable program for causing a computer to translate the original expression in the target document as a translated word as a translated word of the non-translated phrase extracted by the non-translated phrase extraction function 602. The second object is achieved by using a storage medium in which a possible foreign language reading comprehension support program is stored. In the invention described in claim 8, as shown in FIG. 10, a target document acquisition function 601 for acquiring a target document to be translated, and a non-translated word / phrase are extracted from the target document acquired by the target document acquisition function 601. A non-translated word / phrase extraction function 602, a notation conversion function 605 for converting the non-translated word / phrase extracted by the non-translated word / phrase extraction function 602 into a notation based on a translation target word, a translation dictionary 603, and the translation dictionary 603. And a translation function 604 for translating the target document by using the translation function 604 as a translation of the non-translated phrase extracted by the non-translated phrase extraction function 602. And translating the target document by using both the notation converted by the notation conversion function 605 and the original notation in the target document. By computer-readable foreign language text reading support program for realizing to the stored storage medium, it achieves the second object. According to the ninth aspect of the present invention, as shown in FIGS. 9 and 10, in the storage medium storing the foreign language sentence reading support program according to the seventh or eighth aspect, the non-translated phrase extraction function 60 is provided.
2 extracts noun phrases that do not independently exist in the translation dictionary as non-translated phrases. According to the tenth aspect of the present invention, as shown in FIGS. 9 and 10, in the storage medium storing the foreign language sentence reading support program according to the seventh or eighth aspect, the non-translated phrase extraction function 602 is provided.
Extracts compound noun phrases as non-translated phrases. Claim 1
According to the invention described in Item 1, in the storage medium storing the foreign language sentence reading support program according to any one of Claims 7 to 10, as shown in FIG. The translation function 604 includes an importance determination function 607 for determining the importance of the non-translated phrase, and the translation function 604 distinguishes the non-translated phrase from other translation parts according to the importance determined by the importance determination function 607. indicate. In the invention according to claim 12, as shown in FIG.
A storage medium storing the foreign language sentence reading support program according to any one of claims 7 to 11, wherein a paragraph, a sentence, and a paragraph of the target document acquired by the target document acquisition function 601 are provided. A search function 608 for searching for a similar document or a related description for at least one unit of the non-translated phrase, and an association function 609 for associating the similar document or the related description searched by the search function 608 with the corresponding unit. Let it. 14. The foreign language sentence reading comprehension support method according to claim 13, wherein when translating the target document using a translation dictionary, a non-translated phrase is extracted from the target document to be translated 701, and the translated word of the extracted non-translated phrase is extracted. The translation 702 is performed using at least one of a notation of a non-translated phrase converted into a notation using a translation target word and an original sentence table in the target document.

[0006]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, preferred embodiments of a foreign language sentence reading support system, a storage medium storing a foreign language sentence reading support program, and a foreign language sentence reading assisting method of the present invention will be described with reference to FIGS. It will be described with reference to FIG. (1) Overview of Embodiment In the foreign language sentence reading support according to the present embodiment, first, a predetermined non-translated phrase such as a compound noun phrase is extracted from a document to be translated (English or the like) by natural language processing. Then, the entire target document is translated by converting the non-translated words and phrases into katakana notation without translating the words. By doing so, for example, by writing katakana as "action manager" without translating "Action Manager" strangely, it becomes easy to read the entire sentence that knows the content. Also, even a user who does not know the content can read the other parts on the premise that it is a special word, rather than a verbatim translation whose meaning is unknown, so that the user can proceed without confusion.

(2) Details of the Embodiment The foreign language reading comprehension support system of the present embodiment is not only constituted by a computer system including a personal computer and a word processor, but also by a LAN (local area network) server and computer. (Personal computer) It is also possible to configure by a communication host, a computer system connected on the Internet, and the like. In addition, it is also possible to distribute functions to each device on the network and configure a foreign language sentence reading support system on the entire network.

FIG. 1 is a block diagram showing the configuration of a foreign language sentence reading support system. The foreign language reading comprehension support system includes a control unit 11 for controlling the entire system as shown in FIG. The control unit 11 includes a keyboard 12 and a mouse 13 as input devices, a display device 14, and a printing device 1 via a bus line 21 such as a data bus.
5, a storage device 16, a storage medium driving device 17, a communication control device 18, an input / output I / F 19, and a character recognition device 20 are connected. The control unit 11 includes a CPU 111, a ROM 1
12, a RAM 113 is provided. ROM 112
It is a read-only memory in which various programs and data for the PU 111 to perform various controls and calculations are stored in advance.

The RAM 113 is a random access memory used as a working memory for the CPU 111. In the RAM 113, a target document storage area 1131 in which a target document to be translated is stored as an area for performing the foreign language sentence reading support processing according to the present embodiment.
A non-translated word storage area 1132 for storing non-translated words extracted as non-translated words from the target document and their katakana notation, and a translated document storage area for storing translated documents translated using katakana notation for non-translated words. 1133
Other various areas are secured.

The keyboard 12 constitutes a part of a target document acquisition unit or another language input unit for inputting a target document or another language in the own system, and includes a kana key and a numeric keypad for inputting a kana character. Various keys such as a function key and a cursor key for executing a function are arranged. The mouse 13 is a pointing device, and is an input device for designating a corresponding function by left-clicking a key, an icon, or the like displayed on the display device 14. As the display device 14, for example, a CRT or a liquid crystal display is used. The display device includes a keyboard 12 and a mouse 13
Is displayed, and a target document, a translated document, and the like in the foreign language sentence reading support process are displayed. The printing device 15 is for printing documents displayed on the display device 14, documents stored in the document storage unit 164 of the storage device 16, and bills to the user. Various printing apparatuses such as a laser printer, a dot printer, an ink jet printer, a page printer, a thermal printer, and a thermal transfer printer are used as the printing apparatus.

The storage device 16 comprises a readable and writable storage medium and a drive device for reading and writing various information such as programs and data on the storage medium.
As a storage medium used for the storage device 16, a hard disk is mainly used, but a readable and writable storage medium among various storage media used in a storage medium driving device 17 described later may be used. Good. The storage device 16 stores the kana-kanji conversion dictionary 161 and the program storage unit 1
62, a data storage unit 163, a document database 164,
It has an access history database 165, a translation dictionary 165 used for translation, and other storage units (not shown) (for example, storage units for backing up programs and data stored in the storage device 16). I have.
The program storage unit 162 stores, in addition to various programs such as a foreign language sentence reading support processing program and a non-translated phrase extraction program according to the present embodiment, a kana character string input using the kana-kanji conversion dictionary 161 in a kanji mixed sentence. Various programs, such as a kana-kanji conversion program, are stored. The data storage unit 163 stores various data required by the system, such as data on the user. The document database 164 mainly stores many Japanese documents. If necessary, a similar document similar to a predetermined document or the like is searched from the Japanese document. The format of each document stored in the document database 164 is not particularly limited, and various types of documents such as text format documents, HTML (Hyper Text Markup Language) format documents, and JIS format documents can be stored. It is possible.

The storage medium drive 17 is a drive for the CPU 111 to read a computer program or data including a document from an external storage medium. Computer programs and the like stored in the storage medium include various processing programs such as a foreign language sentence reading support process executed by the foreign language sentence reading support system of the present embodiment, and
The dictionary, data, etc. used there are also included. here,
The storage medium refers to a storage medium in which computer programs, data, and the like are stored, and specifically, a magnetic storage medium such as a floppy disk, a hard disk, a magnetic tape,
Semiconductor storage media such as memory chips and IC cards, CD-
A storage medium such as ROM, MO, and PD (phase change rewritable optical disk) from which information can be read optically; a storage medium using paper (such as a paper card or paper tape) (and a medium having a function equivalent to paper); In addition, a storage medium that stores a computer program or the like by various methods is included. As a storage medium used in the foreign language sentence reading support system of the present embodiment, a CD-ROM or a floppy disk is mainly used. The storage medium drive 17 can read data stored in the RAM 113 or the storage device 16 into a writable storage medium such as a floppy disk in addition to reading a computer program from these various storage media. It is.

In the foreign language sentence reading support system of the present embodiment, the CPU 111 of the control unit 11
The computer program is read from an external storage medium set in 7 and stored (installed) in each section of the storage device 16. When executing various processes such as the foreign language sentence reading support process according to the present embodiment, the storage device 16
The corresponding program is read into the RAM 113 and executed. However, it is also possible to read the program directly from the external storage medium into the RAM 113 by the storage medium driving device 17 and execute the program instead of the storage device 16. In addition, depending on the foreign language reading comprehension support system, the foreign language reading comprehension support processing program or the like of this embodiment is stored in the ROM 112 in advance, and this is stored in the CPU 1.
11 may be executed. Furthermore, various programs and data such as the foreign language sentence reading support processing program of the present embodiment may be downloaded from another storage medium via the communication control device 18 and executed.

The communication control device 18 is a control device for connecting a network between the foreign language sentence reading support system and various electronic devices such as personal computers and word processors. The communication control device 18 can access a document in the same language as the target document of these various electronic devices, a document in another language input, and a database of documents in the same language or another language as search targets. It is possible. Target documents include text format and H
In addition to documents in various formats such as TML format, various data such as bitmap data are included. The input / output I / F 19 is an interface for connecting various devices such as a speaker that outputs audio, music, and the like. Character recognition device 20
Is to convert characters written on paper etc. into text format or HTML
And the like, and is constituted by an image scanner, a character recognition program, and the like.

In this embodiment, in addition to a document created by an input operation of the keyboard 12 (stored in a predetermined storage area of the RAM 113), an externally created document read from a storage medium by the storage medium drive 17, a document database , A document downloaded from the communication control device 18, and a character recognized by the character recognition device 20, etc., can be obtained as target documents to be translated (document obtaining means). It is.

The operation of the foreign language reading comprehension support processing by the foreign language reading comprehension support system of the present embodiment configured as described above will be described with reference to FIGS. In the present embodiment, a document (original text) desired to be translated is described in English, and a case where this is translated into Japanese will be described as an example.

FIG. 2 is a flowchart showing the main operation of the foreign language sentence reading support process. The CPU 111 first applies to the target document (original text) for which foreign language sentence reading support (translation) is desired.
Is obtained (step 11).

Then, the language of the original sentence (for example, English), the translation language (for example, Japanese), and the display format specified by the input device such as the keyboard 12 and the mouse 13 are acquired, and the RAM is obtained.
It is stored in a predetermined storage area 113 (step 12).
Here, if the source language is not specified by the user,
The CPU 111 analyzes the acquired target document and specifies a language. Analysis is performed by checking for the presence of written characters unique to each language. In addition, since the user selection of the translation language is an essential item in principle, if no selection is made,
Prompt for selection by screen display. However, when the foreign language sentence reading support system can perform only one type of translation (for example, only English to Japanese), it is not necessary to acquire and store the original language and the translated language. The CPU 111 is a source language,
When acquiring a translation language and a display format, a combination of languages that can be translated and a display format are displayed on a screen so that the user can select the language and the display format.

Next, the CPU 111 activates a non-translated word / phrase extraction program corresponding to the source language from the target document stored in the target document storage area 1132 of the RAM 113,
The non-translated words / phrases are extracted by the resource language processing (NLP), and the extracted non-translated words / phrases (notation of the original text) are stored in the non-translated words / phrases storage area 11
32 (step 13). Here, compound noun phrases are extracted as examples of phrases to be extracted as non-translated phrases, such as noun + pronoun, noun + proper noun, proper noun + article + common noun (eg; Billy the kid), Adjective + ordinary noun + proper noun (eg; Mad scientist Doctor E
mett Brown). For further example, if the source language is English, "An incremental utterance taskoriented
dialogue production system '', `` An Internet based
wide area computer assisted foreign language lear
Compound noun phrases such as "ning prototype demonstration system" are extracted as untranslated phrases.

Next, the CPU 111 checks whether or not the display format specified in step 12 is a display format including katakana display (step 14). If the display format includes the katakana display (Y), the non-translated words extracted in step 13 are converted into katakana notation (notation conversion means).
The katakana notation converted corresponding to the non-translated phrase is stored in the non-translated phrase storage area 1132 (step 15).
Here, the conversion of non-translated words into katakana notation is performed by reading Roman characters when the original sentence is in English, or by using phonetic symbols of each word.

Then, the CPU 111 executes the translation dictionary 165
The target document is translated using the non-translated phrase and / or katakana notation (selected according to the selected display format) stored in the non-translated phrase storage area 1132, and the translation result is stored in the translated document storage area 1133. (Step 1
6). When the translation is completed, the CPU 111
Is displayed in the designated display format (step 17), and the process ends.

FIG. 3 shows “Katakana notation” as a display format.
13 shows a display screen of a translation result when is selected. In FIG. 3, the original sentence (target document) and the Japanese translation result are displayed horizontally, but it is also possible to display only one of them or to display it vertically. is there. As shown in this figure, the untranslated phrase "Action
The word "Manager" is not translated literally into meaningless words such as "acting section manager", but is collectively written in katakana as "action manager", so that a user who knows the language can immediately understand it. Also, even a user who does not know the language can be confused because the entire sentence can not be understood by a literal translation that has no meaning and can read other parts on the assumption that it is a special word. You can read without reading.

FIGS. 4A and 4B show a display screen when another display format is selected. FIG. 4A shows a display screen of “original text notation”, and FIG. 4B shows a display screen of “Katakana notation (original text notation)”. Are displayed. As shown in this figure,
By using the original language notation, users who have the language skills of the original language can immediately understand the contents from the original language notation, and for those who do not, clearly identify the words that must be looked up from the original language notation using a dictionary etc. can do. Although not shown, when “Original notation (Katakana notation)” is selected as the display format, “Action Manager” is displayed for the non-translated phrase “Action Manager”.

In the above, the processing for translating the target document according to the present embodiment in a mixture of the katakana notation and the original sentence notation has been described. However, the following processing may be further performed. That is, the importance of the non-translated phrase extracted in step 13 is determined using the target document, and the original text and katakana text in the translated sentence of the translation result are specially displayed according to the importance. To do it. As the distinction display between the original notation and the katakana notation, emphasis may be performed using character decoration information such as color, density, character size, and character thickness, or reverse emphasis may be performed. The emphasis is high when the importance is high. The emphasis is emphasized by at least one of a conspicuous color such as red, high density, enlarged characters (the size is changed according to the importance), and bold characters. Inverse emphasis is performed when the degree of importance is low. Inverse emphasis is performed so as to be inconspicuous by one or more of inconspicuous colors such as light blue and gray, low density, reduced characters, and fine characters.

As a method of determining the importance of a non-translated phrase,
Various proposed known important word determination methods are used.
For example, the PU 111 performs a morphological analysis, extracts an independent word from the target document, and sets it as a candidate word. Then, the importance of each candidate word is determined from the appearance frequency of the extracted candidate word in the target document and the evaluation function, and the candidate word having the importance equal to or higher than a certain threshold is determined as the important word. Here, as the evaluation function,
For example, when a predetermined word is specified in advance, weighting for that word is used. Then, important word candidates appearing in the non-translated words are checked, and the total value of the importance is set as the importance of the non-translated words.

As a method for judging the importance of a non-translated phrase, "extraction and processing of semantic information from full-text information" (Information Processing Society of Japan 38th Annual Conference Proceedings, p. 222; 198)
As proposed in (9th year), important words in a document may be extracted from information such as character types and verbs to make a determination.

Further, in addition to the process of translating a target document according to the present embodiment in a mixture of katakana and original sentences, the following process may be further performed. That is, a similar document or a related description is searched for at least one of a paragraph, a sentence, and a non-translated phrase in the target document acquired in step 11, and a hyperlink is attached. Then, when the user scrolls or moves the mouse cursor over the relevant portion, the related document name list and a part of the document content (head and summary) are displayed in a balloon (balloon) to assist understanding. At this time, the related document in the native language may be preferentially displayed.

Here, for searching for similar documents, various known search methods can be used. For example, a document vector (a vector having the importance of a keyword included in the document as an element) representing the characteristics of the document can be used. The similarity between the two documents is determined by the cosine depending on the angle between the document vectors for the two documents as follows. That is, if the angle between the two document vectors bn and bn + 1 is q, the inner product of both document vectors is bn · bn + 1, and the size of both document vectors is | bn | and | bn + 1 | The degree Snn + 1 is obtained by the following equation (1).

[0029]

(1) Similarity Snn + 1 = COS (q) = (bn · bn + 1) / (| bn | × | bn + 1 |)

The value of the similarity S takes a value up to −1 ≦ S ≦ 1, and as the value is closer to 1, the two document vectors are closer to each other in parallel, and it can be considered that the two documents are similar. Therefore, a document having a similarity equal to or higher than a certain threshold value is determined as a similar document, and is set as a search result.

Although the configuration of this embodiment and the processing for assisting in reading a foreign language sentence have been described above, the present invention is not limited to each of these forms, and various modifications are possible within the scope of the invention described in the claims. Can be modified.
For example, in the embodiment, English has been described as an example of the language (source language) of the target document and Japanese has been described as the translation language. However, the present invention is not limited to these combinations, and may be any combination between languages. It is possible. In this case, it is only necessary to change a portion that does not affect the configuration of the present invention, such as using a morphological analysis algorithm for the language in which the target document is created.

Each device, each unit, each operation, each process, and the like described in the above embodiment can be constituted by each unit as a high-level concept including these units. It is. For example, the "similarity calculating means" may be configured for the description "the similarity between the two documents is obtained by the cosine depending on the angle between the document vectors for the two documents as follows". Similarly, the embodiment may be configured with a higher concept such as “「 (operation) means ”for various other operations.

[0033]

According to the present invention, when translating the target document using the translation dictionary, a non-translated word is extracted from the target document to be translated, and the translated non-translated word is translated as a translation of the extracted non-translated word. Since the translation is performed using at least one of the notation of the non-translated phrase converted into the notation in the target word and the original text table in the target document, a more natural translation result is provided, Word reading comprehension is supported.

[Brief description of the drawings]

FIG. 1 is a block diagram showing a configuration of a foreign language sentence reading support system according to an embodiment of the present invention.

FIG. 2 is a flowchart showing a main operation of a foreign language sentence reading support process according to the embodiment.

FIG. 3 is an explanatory diagram showing a translation result display screen when “Katakana notation” is selected as a display format in the embodiment.

FIG. 4 shows a display screen when another display format in the embodiment is selected, wherein (A) is a display screen of “original text notation”, and (B) is “display of katakana notation (original text notation)”. It is an explanatory view showing a display screen of "".

FIG. 5 is a diagram corresponding to claims of the invention described in claim 1;

FIG. 6 is a diagram corresponding to claims of the invention described in claim 2;

FIG. 7 is a diagram corresponding to claim 5 of the invention described in claim 5;
It is an example.

FIG. 8 is a diagram corresponding to claim 6 of the invention described in claim 6;
It is an example.

FIG. 9 is a diagram corresponding to claims of the invention described in claim 7;

FIG. 10 is a diagram corresponding to claims of the invention described in claim 8;

FIG. 11 is an example of a claim correspondence diagram of the invention described in claim 11;

FIG. 12 is an example of a claim correspondence diagram of the invention described in claim 12;

FIG. 13 is a diagram corresponding to claims of the invention described in claim 13;

FIG. 14 is an explanatory diagram showing a conventional translation result.

[Explanation of symbols]

 11 control unit 112 ROM 113 RAM 1131 target document storage area 1132 untranslated words / phrases storage area 1133 translated document storage area 12 keyboard 13 mouse 14 display device 15 printing device 16 storage device 161 kana-kanji conversion dictionary 162 program storage unit 163 data storage unit 164 Document database 165 Translation dictionary 17 Storage medium drive 18 Communication control device 19 Input / output I / F 20 Character recognition device

Claims (13)

[Claims] 1. A target document acquisition unit for acquiring a target document to be translated, a non-translated phrase extraction unit for extracting a non-translated phrase from the target document acquired by the target document acquisition unit, a translation dictionary, A translation unit for translating the target document using a translation dictionary, wherein the translation unit translates the original notation in the target document as a translation of the non-translated phrase extracted by the non-translated phrase extraction unit. A foreign language reading comprehension support system characterized by doing. 2. A target document acquisition unit for acquiring a target document to be translated, a non-translated phrase extraction unit for extracting a non-translated phrase from the target document acquired by the target document acquisition unit, and the non-translated phrase extraction A notation conversion unit that converts the non-translated phrase extracted by the unit into a notation in a translation target word; a translation dictionary; and a translation unit that translates the target document using the translation dictionary. As a translation of the non-translated phrase extracted by the non-translated phrase extraction means, the notation converted by the notation conversion means, or both the notation converted by the notation conversion means and the original notation in the target document A foreign language reading comprehension support system characterized in that the target document is used for translation. 3. The foreign language phrase according to claim 1, wherein the non-translated phrase extraction means extracts a noun phrase that does not exist independently in the translation dictionary as a non-translated phrase. Word reading support system. 4. The foreign language sentence reading support system according to claim 1, wherein said non-translated phrase extraction means extracts a compound noun phrase as a non-translated phrase. 5. An importance judging means for judging importance of the non-translated phrase, wherein the translating means converts the non-translated phrase into another translated part according to the importance decided by the importance judging means. The foreign language sentence reading support system according to any one of claims 1 to 4, wherein the foreign language sentence reading support system is displayed in a manner distinguishing from the foreign language sentence. 6. A search means for searching for a similar document or a related description for at least one unit of a paragraph, a sentence, and a non-translated phrase of the target document acquired by the target document acquisition means, and a search by the search means Similar documents or related descriptions
6. An associating means for associating with a corresponding unit, wherein:
Foreign language reading comprehension support system described in the claim. 7. A target document acquisition function for acquiring a target document to be translated, a non-translated phrase extraction function for extracting a non-translated phrase from the target document acquired by the target document acquisition function, a translation dictionary, A translation function of translating the target document using a translation dictionary, wherein the translation function translates the original sentence notation in the target document as a translation of the non-translated phrase extracted by the non-translated phrase extraction function. A storage medium storing a computer-readable foreign-language sentence reading support program for causing a computer to perform the processing. 8. A target document acquisition function for acquiring a target document to be translated, a non-translated phrase extraction function for extracting a non-translated phrase from the target document acquired by the target document acquisition function, and the non-translated phrase extraction A translation function for translating a non-translated phrase extracted by the function into a representation by a translation target word; a translation dictionary; and a translation function for translating the target document using the translation dictionary. As a translation of the non-translated phrase extracted by the non-translated phrase extraction function, the notation converted by the notation conversion function, or both the notation converted by the notation conversion function and the original notation in the target document A storage medium storing a computer-readable foreign language sentence reading support program for causing a computer to translate the target document by using the program. 9. The foreign language according to claim 7, wherein the non-translated phrase extraction function extracts a noun phrase that does not exist independently in the translation dictionary as a non-translated phrase. A storage medium in which a word and sentence reading support program is stored. 10. The storage medium storing a foreign language sentence reading support program according to claim 7, wherein the non-translated phrase extraction function extracts a compound noun phrase as a non-translated phrase. . 11. An importance determining function for determining the importance of the non-translated phrase, wherein the translation function converts the non-translated phrase into another translation part according to the importance determined by the importance determining function. A storage medium storing the foreign language sentence reading support program according to any one of claims 7 to 10, wherein the storage medium stores the foreign language sentence reading support program. 12. A search function for searching for a similar document or a related description for at least one unit of a paragraph, a sentence, and a non-translated phrase of the target document obtained by the target document obtaining function; Similar documents or related descriptions
The storage medium storing the foreign language sentence reading support program according to any one of claims 7 to 11, further comprising an association function of associating the foreign language sentence with the corresponding unit. 13. When translating the target document using a translation dictionary, extract a non-translated phrase from the target document to be translated, and convert the extracted non-translated phrase into a notation in the translation target word as a translation of the extracted non-translated phrase. A foreign language reading comprehension support method, characterized in that translation is performed using at least one of a notation of a non-translated word and a source sentence table in the target document.