JP2893740B2 - Machine translation equipment - Google Patents
Machine translation equipmentInfo
- Publication number
- JP2893740B2 JP2893740B2 JP1200610A JP20061089A JP2893740B2 JP 2893740 B2 JP2893740 B2 JP 2893740B2 JP 1200610 A JP1200610 A JP 1200610A JP 20061089 A JP20061089 A JP 20061089A JP 2893740 B2 JP2893740 B2 JP 2893740B2
- Authority
- JP
- Japan
- Prior art keywords
- translation
- words
- unregistered
- language
- target language
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Lifetime
Links
- 238000013519 translation Methods 0.000 title claims description 34
- 238000003780 insertion Methods 0.000 claims description 6
- 230000037431 insertion Effects 0.000 claims description 6
- 239000000284 extract Substances 0.000 claims description 2
- 230000000877 morphologic effect Effects 0.000 description 5
- 238000000605 extraction Methods 0.000 description 4
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000003058 natural language processing Methods 0.000 description 2
- 238000007796 conventional method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000000034 method Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
Landscapes
- Machine Translation (AREA)
Description
【発明の詳細な説明】 〔産業上の利用分野〕 本発明は、入力文中に翻訳目標言語の単語が含まれる
文章を翻訳する機能を有する機械翻訳装置に関するもの
である。Description: TECHNICAL FIELD The present invention relates to a machine translation device having a function of translating a sentence in which an input sentence includes words in a target language.
近年、自然言語処理技術の発達に伴い、機械翻訳シス
テムの開発が盛んになってきている。私的な文書におい
ては英語の単語をそのまま文中に書くことが頻繁に起こ
るが、従来の翻訳システムでは、例えば日英翻訳システ
ムを例に取ると文中の英語の単語は未登録語としてしか
扱うことができない。未登録語として扱われた語は、訳
文中の適当な箇所に原文中の形態のままで挿入される。2. Description of the Related Art In recent years, with the development of natural language processing technology, development of a machine translation system has been active. In private documents, English words are often written in sentences as they are, but conventional translation systems treat English words in sentences as unregistered words, for example, using a Japanese-English translation system as an example. Can not. Words that have been treated as unregistered words are inserted at appropriate places in the translated text as they are in the original text.
従来の技術で未登録語として扱われた目標言語の単語
がたとえば訳文中の正しい場所に挿入されたとしても、
入力文中の形態のままで表示されてしまうために、例え
ば、複数形にすべきところを単数形で表示したり、過去
形にすべきところを現在形で表示したりするというよう
に、例えば“system were integrate"の如き文法的に誤
った文を生成してしまう欠点があった。本発明の目的
は、原文中の目標言語の単語の構文的な情報を利用して
正しい形態素を表示することができる機械翻訳装置を提
供することにある。Even if the target language word, which was treated as an unregistered word in the conventional technology, was inserted in the correct place in the translation, for example,
In order to be displayed as it is in the form of the input sentence, for example, a place to be pluralized is displayed in singular form, and a place to be past form is displayed in present form, for example, " It had the disadvantage of generating grammatically incorrect sentences such as "system were integrate". An object of the present invention is to provide a machine translator capable of displaying a correct morpheme using syntactic information of a word in a target language in an original sentence.
本発明による機械翻訳装置は、翻訳の目標言語の単語
が混在している文章を入力し翻訳を行う装置において、
入力した複数言語混在文に含まれる未登録語を抽出する
未登録語抽出装置と、目標言語辞書と、抽出した未登録
語の中から目標の単語を抽出し保持する外語保持装置
と、未登録語を含む文の翻訳を行う翻訳装置と、該単語
を訳文中に埋め込む外語挿入装置とを備えて構成され
る。A machine translation device according to the present invention is a device that performs a translation by inputting a sentence in which words in a target language of translation are mixed,
An unregistered word extraction device for extracting unregistered words contained in the input multi-language mixed sentence, a target language dictionary, a foreign word holding device for extracting and holding a target word from the extracted unregistered words, and an unregistered word It comprises a translation device for translating a sentence including a word, and an external word insertion device for embedding the word in the translation.
本発明について図面を参照して説明する。 The present invention will be described with reference to the drawings.
第１図は本発明の一実施例を示すブロック図である。
ここでは説明のために原言語が日本語で目標言語が英語
であるような翻訳装置を例に取って説明するが、他の言
語対においても全く同じの構成で同じ効果を持つ機械翻
訳装置が実現できる。FIG. 1 is a block diagram showing one embodiment of the present invention.
Here, for the sake of explanation, a translation device in which the source language is Japanese and the target language is English will be described as an example. realizable.
未登録語抽出装置１に第２図（ａ）に示すような翻訳
の目標言語を含む入力文が入力されると、形態素解析に
より入力文を辞書登録語単位に語分割し同時に未登録語
を抽出する。例えば、第２図（ａ）の入力文に対して語
分割を行った結果「２」「つ」「の」「system」「を」
「integrate」「し」「ました」「。」というように語
分割され、このうち「system」と「integrate」が日本
語辞書未登録語として抽出される。抽出された未登録語
は識別番号と共にデータ線12を介して外語保持装置２に
送出される。第２図（ｂ）にデータ線12を介して送られ
るデータの例を示す。また同時に、未登録語抽出装置１
で語分割された結果はデータ線13を介して翻訳装置３に
送出される。第２図（ｃ）にデータ線13を介して送られ
るデータの例を示す。When an input sentence including a target language for translation as shown in FIG. 2 (a) is input to the unregistered word extraction device 1, the input sentence is divided into dictionary registered words by morphological analysis, and unregistered words are simultaneously extracted. Extract. For example, as a result of performing word segmentation on the input sentence of FIG. 2 (a), "2""tsu""no""system""wo"
Words are divided into "integrate", "shi", "was", ".", And "system" and "integrate" are extracted as unregistered words in the Japanese dictionary. The extracted unregistered word is sent to the external word holding device 2 via the data line 12 together with the identification number. FIG. 2 (b) shows an example of data sent via the data line 12. At the same time, the unregistered word extraction device 1
Is sent to the translation device 3 via the data line 13. FIG. 2 (c) shows an example of data transmitted via the data line 13.
外語保持装置２では、送られたきた未登録語をキーに
してデータ線24を介し目標言語辞書４を検索し、目標言
語辞書４に該未登録語が存在する場合は、品詞や屈折形
等の統語的、形態的情報を該未登録語に付与し、目標言
語辞書に該未登録語が存在しない場合は、存在しないと
いう印を該未登録語に与える。その結果をデータ線25を
介して外語挿入装置５に送出する。第２図（ｄ）にデー
タ線25を介して送られるデータの例を示す。The foreign language holding device 2 searches the target language dictionary 4 via the data line 24 using the sent unregistered word as a key, and if the unregistered word exists in the target language dictionary 4, the part-of-speech, inflection form, etc. Is given to the unregistered word, and if the unregistered word does not exist in the target language dictionary, a mark indicating that it does not exist is given to the unregistered word. The result is transmitted to the external language insertion device 5 via the data line 25. FIG. 2 (d) shows an example of data sent via the data line 25.
翻訳装置３では語分割された入力文に対して翻訳を行
う。このとき、未登録語に対する品詞推定、訳文での形
態的属性の付与も同時に行われる。例えば、「system」
に関しては直後の「を」により「system」が名詞である
ことがわかり、更に直前の「２つの」により「system」
が複数であることが推定できる。また、「integrate」
に関しては直後の「し」、「ました」により「integrat
e」が動詞であり、動詞句の時制は過去であることが推
定できる。翻訳結果である訳文中の未登録語に対応する
部分には識別番号と品詞、単複の別、時制情報等の統語
・形態情報が与えられる。第２図（ｅ）に翻訳装置３の
出力例を示す。翻訳装置３の出力はデータ線35を介して
外語挿入装置５に送出される。The translation device 3 translates the input sentence that has been divided into words. At this time, the part-of-speech estimation for the unregistered word and the addition of the morphological attribute in the translated sentence are performed at the same time. For example, "system"
As for, "system" immediately following "wo" indicates that "system" is a noun.
Can be estimated to be plural. Also, "integrate"
With regard to "integrat"
"e" is a verb, and it can be inferred that the tense of the verb phrase is in the past. The part corresponding to the unregistered word in the translated sentence as the translation result is provided with an identification number and a part of speech, syntactic / morphological information such as single or plural, tense information, and the like. FIG. 2 (e) shows an output example of the translation device 3. The output of the translation device 3 is sent to the foreign language insertion device 5 via the data line 35.
外語挿入装置５は、翻訳装置３から送られてきた訳文
の骨格と、外部保持装置から送られてきた目標言語の単
語に関する情報とから、最終的な訳文を作成する。「sy
stem」は複数であるという情報から複数形“systems"が
選択され、「integrate」は過去時制で受動態で主語が
三人称複数であるという情報から“were integrated"と
いう形態素で訳出される。第２図（ｆ）に最終的な訳文
を示す。The foreign language insertion device 5 creates a final translation from the skeleton of the translation sent from the translation device 3 and the information on the word in the target language sent from the external holding device. "Sy
The plural form "systems" is selected from the information that the "stem" is plural, and "integrate" is translated into the morpheme "were integrated" from the information that the subject is a third person plural in the past tense in the passive voice. FIG. 2 (f) shows the final translation.
本発明によれば、翻訳目標言語の単語を含む入力文を
翻訳する場合に、形態素解析部で抽出された未登録語に
ついて翻訳対象言語辞書を引くことにより、形態的、統
語的情報を抽出し文法的に正しい訳文を生成することが
できる。（従来の方法では、屈折形や複数形に関する情
報がないので、例えば例にあげた入力文にたいして“2
system were integrate."という非文法的な訳文が生成
されてしまう。）According to the present invention, when translating an input sentence including a word in a translation target language, morphological and syntactic information is extracted by referencing a translation target language dictionary for unregistered words extracted by the morphological analysis unit. A grammatically correct translation can be generated. (In the conventional method, since there is no information on the refraction and plural forms, for example, "2
An ungrammatical translation, "system were integrate."
第１図は本発明の機械翻訳装置の一実施例の構成を示す
ブロック図、第２図（ａ）〜（ｆ）は翻訳装置の入力文
の例と各過程で授受されるデータの一例である。 １……未登録語抽出装置、２……外語保持装置、３……
翻訳装置、４……目標言語辞書、５……外語挿入装置を
しめす。FIG. 1 is a block diagram showing the configuration of an embodiment of a machine translation apparatus according to the present invention. FIGS. 2 (a) to 2 (f) show examples of input sentences of the translation apparatus and examples of data transmitted and received in each process. is there. 1 ... unregistered word extraction device, 2 ... foreign word holding device, 3 ...
Translation device 4, target language dictionary 5, foreign language insertion device.
フロントページの続き (56)参考文献 特開 昭61−33577（ＪＰ，Ａ) 特開 平２−33664（ＪＰ，Ａ) 特開 昭63−68972（ＪＰ，Ａ) 特開 昭57−111669（ＪＰ，Ａ) 特開 昭58−175075（ＪＰ，Ａ) 特開 昭63−300359（ＪＰ，Ａ) 長尾真，辻井潤一，伊吹潤、上田良 寛，「論文表題の日英機械翻訳システ ム」，情報処理学会自然言語処理研究会 資料，34−４，Ｐ．19−Ｐ．26（1982) (58)調査した分野(Int.Cl.6，ＤＢ名) G06F 17/20 - 17/28 ＪＩＣＳＴファイル（ＪＯＩＳ)Continuation of the front page (56) References JP-A-61-33577 (JP, A) JP-A-2-33664 (JP, A) JP-A-63-68972 (JP, A) JP-A-57-111669 (JP) , A) JP-A-58-175075 (JP, A) JP-A-63-300359 (JP, A) Makoto Nagao, Junichi Tsujii, Jun Ibuki, Yoshihiro Ueda, "Japanese-English Machine Translation System for Title of Papers", Information Processing Society of Japan, Natural Language Processing Study Group, Material 34-4, p. 19-P. 26 (1982) (58) Fields surveyed (Int. Cl. 6 , DB name) G06F 17/20-17/28 JICST file (JOIS)
Claims (1)
を入力し翻訳を行う装置において、入力した複数言語混
在文に含まれる未登録語を抽出する未登録語抽出装置
と、目標言語辞書と、抽出した未登録語の中から目標言
語の単語を抽出し保持する外語保持装置と、未登録語を
含む文の翻訳を行う翻訳装置と、前記目標言語辞書を参
照し該単語の構文上適合する形態を訳文中に埋め込む外
語挿入装置とを備えて成ることを特徴とする機械翻訳装
置。An apparatus for inputting and translating a sentence in which words in a target language of translation are mixed, wherein an unregistered word extracting apparatus for extracting unregistered words included in the input multi-language mixed sentence, and a target language A dictionary, a foreign language holding device that extracts and holds words of the target language from the extracted unregistered words, a translation device that translates a sentence containing the unregistered words, and a syntax of the words by referring to the target language dictionary A machine translation device, comprising: a foreign language insertion device that embeds a form suitable for the above into a translation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP1200610A JP2893740B2 (en) | 1989-08-01 | 1989-08-01 | Machine translation equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP1200610A JP2893740B2 (en) | 1989-08-01 | 1989-08-01 | Machine translation equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| JPH0363764A JPH0363764A (en) | 1991-03-19 |
| JP2893740B2 true JP2893740B2 (en) | 1999-05-24 |
Family
ID=16427230
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| JP1200610A Expired - Lifetime JP2893740B2 (en) | 1989-08-01 | 1989-08-01 | Machine translation equipment |
Country Status (1)
| Country | Link |
|---|---|
| JP (1) | JP2893740B2 (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6024072A (en) * | 1997-05-21 | 2000-02-15 | Aisan Kogyo Kabushiki Kaisha | Fuel pump control apparatus |
-
1989
- 1989-08-01 JP JP1200610A patent/JP2893740B2/en not_active Expired - Lifetime
Non-Patent Citations (1)
| Title |
|---|
| 長尾真，辻井潤一，伊吹潤、上田良寛，「論文表題の日英機械翻訳システム」，情報処理学会自然言語処理研究会資料，３４−４，Ｐ．１９−Ｐ．２６（１９８２） |
Also Published As
| Publication number | Publication date |
|---|---|
| JPH0363764A (en) | 1991-03-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP3220560B2 (en) | Machine translation equipment | |
| US7031911B2 (en) | System and method for automatic detection of collocation mistakes in documents | |
| KR101130444B1 (en) | System for identifying paraphrases using machine translation techniques | |
| Hutchins | Towards a definition of example-based machine translation | |
| JPH0782498B2 (en) | Machine translation system | |
| JPH07282055A (en) | Sentence analysis method and device | |
| Hutchins | Machine translation: History and general principles | |
| JP2893740B2 (en) | Machine translation equipment | |
| Lamb | The nature of the machine translation problem | |
| Tokuda et al. | Towards automatic translation from japanese into japanese sign language | |
| JPS59140582A (en) | Natural language translation assisting system | |
| JP2000250913A (en) | Example-type natural language translation method, bilingual example collection creating method and apparatus, and recording medium recording the program thereof | |
| Filip et al. | Text normalization as a special case of machine translation | |
| Ohtake et al. | Applicability analysis of corpus-derived paraphrases toward example-based paraphrasing | |
| JP2972212B2 (en) | Machine translation method and system | |
| JP2928246B2 (en) | Translation support device | |
| Moon et al. | Translation of discontinuous multi-word translation units in a korean-to-japanese machine translation system | |
| JP4023384B2 (en) | Natural language translation method and apparatus and natural language translation program | |
| JP2007072841A (en) | Word extraction method, database construction method, database construction device, database construction program, and recording medium | |
| Vanni et al. | The Temple translator’s workstation project | |
| JP3873653B2 (en) | Dictionary creating method and apparatus, dictionary creating program, and storage medium storing dictionary creating program | |
| JP2947554B2 (en) | Machine translation equipment | |
| JPH0340067A (en) | Sentence retrieving system | |
| Rao et al. | Gentle Introduction‖ | |
| JPH03211669A (en) | Mechanical translation device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| FPAY | Renewal fee payment (event date is renewal date of database) |
Free format text: PAYMENT UNTIL: 20080305 Year of fee payment: 9 |
|
| FPAY | Renewal fee payment (event date is renewal date of database) |
Free format text: PAYMENT UNTIL: 20090305 Year of fee payment: 10 |
|
| FPAY | Renewal fee payment (event date is renewal date of database) |
Free format text: PAYMENT UNTIL: 20090305 Year of fee payment: 10 |
|
| FPAY | Renewal fee payment (event date is renewal date of database) |
Free format text: PAYMENT UNTIL: 20100305 Year of fee payment: 11 |
|
| EXPY | Cancellation because of completion of term | ||
| FPAY | Renewal fee payment (event date is renewal date of database) |
Free format text: PAYMENT UNTIL: 20100305 Year of fee payment: 11 |