CN107220243A - A kind of Database Interactive translation system - Google Patents
A kind of Database Interactive translation system Download PDFInfo
- Publication number
- CN107220243A CN107220243A CN201710437862.4A CN201710437862A CN107220243A CN 107220243 A CN107220243 A CN 107220243A CN 201710437862 A CN201710437862 A CN 201710437862A CN 107220243 A CN107220243 A CN 107220243A
- Authority
- CN
- China
- Prior art keywords
- database
- translation
- unit
- text
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/40—Processing or translation of natural language
- G06F40/58—Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3325—Reformulation based on results of preceding query
- G06F16/3326—Reformulation based on results of preceding query using relevance feedback from the user, e.g. relevance feedback on documents, documents sets, document terms or passages
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/40—Processing or translation of natural language
- G06F40/51—Translation evaluation
Abstract
The present invention provides a kind of different from existing translation system, and prior art can be overcome not enough, intelligent quick, by being inputted by expert, on-line study, user evaluate, the method such as fan's support, it is on-line automatic to set up database;It is multilingual comprehensive, accurate practical automatic translation system.The technical proposal of the invention is realized in this way:A kind of Database Interactive translation system, it is characterised in that including:Online database, translating equipment;Wherein online database is constituted by including unit, memory cell, retrieval unit, matching unit, output unit;Translating equipment by receiver, discrimination unit, retrieval unit, type judging unit, display output unit, voice-output unit, evaluation unit, edit and record unit and constitute.
Description
Technical field
The present invention relates to language machine translation system field, a kind of Database Interactive translation on line system is refered in particular to.
Background technology
The process of research on the machine translation can trace back to generation 30 or 40 years 20th century.In the early 1930s, French science
The idea that family G.B. A Erchuni propose with machine to be translated.1933, USSR man Te Luoyangsiji was devised
A kind of language translation into the machine of another language, and his invention was registered in 5th in the same year September, still, due to 30 years
Generation technique level is also very low, and his translator is formed without.Nineteen forty-six, First hyundai electronicses computer ENIAC is born, then
Soon, the pioneer of information theory, American scientist W.Weaver and Britain engineer A.D.Booth are discussing answering for electronic computer
When using scope, the idea that automatic language translation is carried out using computer is proposed in nineteen forty-seven.1949, W.Weaver was delivered
《Translate memorandum》, the formal thought for proposing machine translation.The trials and hardships passed by 60 years, machine translation experienced a song
Roll over and very long road for development.
Chinese machine translation research is started in nineteen fifty-seven, be in the world the 4th embark machine translation country, the sixties
Once interrupted after mid-term, there is further development since the mid-1970s.Institute of Linguistics of the Chinese Academy of Social Sciences, China
The units such as Science and Technology Information Institute, Inst. of Computing Techn. Academia Sinica, Heilongjiang University, Harbin Institute of Technology are all
Carrying out research on the machine translation;Upper machine carried out existing more than ten of the machine translation system of experiment, the languages and type of translation
There are the man-to-man systems such as English-Chinese, Russia's Chinese, Fa Han, Han, the moral Chinese, also there is Chinese to English, method, day, Russia, a pair of multisystems of moral
(FAJRA systems).In addition, having also set up a Chinese data storehouse and an English for science and technology corpus.Chinese machine translation system
Scale constantly expand, content is constantly perfect.
The operation principle of above-mentioned translation system, construction primarily directed to corpus and the work, current number such as improves
Mainly use expert's input method and internet learning method according to the method for building up in storehouse, method is more single, occur in that translation it is inaccurate,
Corpus Data Collection is difficult, and languages are single;Especially to literature, ancient books and professional meeting translation, due to translation money
The scarcity of material, work is set up to corpus, causes a variety of difficulties for being difficult to expect.
The content of the invention
It is an object of the invention to provide a kind of different from above-mentioned existing system, prior art can be overcome not enough, intelligence
Fast, by being inputted by expert, on-line study, user evaluate, fan support etc. method it is on-line automatic set up database, it is many
Languages are comprehensive, accurate practical automatic translation system.
The technical proposal of the invention is realized in this way:A kind of Database Interactive translation system, it is characterised in that bag
Include:Online database, translating equipment;Wherein online database by including unit, it is memory cell, retrieval unit, matching unit, defeated
Go out unit composition;Translating equipment is by receiver, discrimination unit, retrieval unit, type judging unit, display output unit, voice
Output unit, evaluation unit, edit and record unit composition.
Further, the online database includes unit, by including from the word in internet, books, dictionary, sentence
Bilingual or multilingual control text sets up basic database, and by constantly including newborn vocabulary and sentence, preserves translation record
Come database of enriching constantly;Database can include a variety of cypher texts (if having) to same source text, and carry out masses to it
The text that scoring determination optimum answer is not classified as optimum answer can be still retained, and database can show a variety of translation knots in translation
Really;Open to include new text data, anyone can all input new text to enrich database;The translation inputted for the public,
The method that database computer processor can be translated by internal machine examines whether translation originally corresponds in source;Database is based on interconnection
Net build, anyone anywhere, any country can supplementary data storehouse data.
Further, the online database memory cell:All words being included with various approach, sentence, text is all
It can be stored in the online database on internet.
Further, the retrieval unit of the online database:Anyone can input the source of any language into database
The translation of sheet and any language, database can carry out classifying and classified storage to language, so that abundant database;It is any to be translated
The source text crossed, can draw, it is to avoid the syntax error being likely to occur when machine is turned over occur directly from database;To ancient Chinese prose, poem
Special word or sentence in word, novel, science fiction works, bilingual or multilingual control is had directly from being extracted in database
Translation or sample, it is to avoid include the situation that word or sentence can not be translated to non-dictionary, or by the special style wind of certain author
Discourse structure of body can not problem analysis caused by lattice.
Further, the matching unit of the online database:Retrieval pairing translation is carried out using stored data in database,
The text of existing translation is directly extracted from database.
Further, the output unit of the online database:The text that can be used through overmatching identification can be output to
Translating equipment.
Further, the translating equipment receiver:Translation on line request for receiving user terminal transmission, it is described online
Translation request is pre-configured in translation software, and the translation on line request is that owning user can not understand the situation of communication information
Lower transmission.
Further, the translating equipment discrimination unit:Sentence for source language text in translation on line request described in discrimination
Son composition and by text segmentation into base text unit.
Further, the translating equipment retrieval unit:Whether have matching usable text, if any then if being retrieved in database
It can be used directly.
Further, the translating equipment type judging unit:Matched text can not be retrieved from database, passes through machine
Turn over and draw translation result.It is that receiver turns over result or obtains translation result by human translation by judgement.
Further, the translating equipment display output unit:From obtained by database retrieval, machine translation or human translation
The result of gained can show text output in the way of source language and target langua0 control.
Further, the translating equipment voice-output unit:Translation produced by database can be both presented with text mode
Also it can be expressed by the form of voice.
Further, the translating equipment evaluation unit:User is evaluated translation result, evaluates optimal translation result.
And include the optimal evaluation result of preservation.
Further, the translating equipment edits and records unit:Database, which can classify, includes the source language text translated every time and right
According to target langua0 text, do next time inquiry using.
Brief description of the drawings
, below will be to prior art in order to clearly illustrate technical scheme of the prior art of the invention and embodiment
Or the accompanying drawing required in embodiment description is briefly described, it is therefore apparent that drawings in the following description are only the present invention
Some embodiments, on the premise of not paying creative work, can be with root for one of ordinary skill in the art
Other accompanying drawings are obtained according to these accompanying drawings.
A kind of Database Interactive translation system Basis of Database integrated approach schematic diagram of the invention of accompanying drawing 1.
A kind of Database Interactive translation system implementation process diagram of the invention of accompanying drawing 2.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Whole description, although described embodiment is only a part of embodiment of the present invention, rather than whole embodiments, is based on
For those of ordinary skill in the art, on the premise of not paying creative work, the every other embodiment obtained all belongs to
In protection scope of the present invention.
As shown in Figure 1, employed in this interpretation method database forming method schematic diagram.Step 101 first:From not
Collected with channel the particular text to form Basis of Database data, style, proper noun, special noun, word, phrase, proverb,
Idiom, Chinese idiom, two-part allegorical saying, clause, sentence pattern, newborn vocabulary, cyberspeak, modish vocabulary, ancient Chinese prose, ancient books, ancient poetry, well-known saying.It is right
The collection content of text includes the source language text of text, target langua0 text (or referenced text).So as to form the base of database
Plinth is integrated.
As shown in Figure 1, formed Basis of Database it is integrated after be to the abundant and perfect of database, the process be not between
Disconnected, it can be enriched constantly and perfect with each use, inquiry or the passage of time.The supply approach of database is included from mutually
Newborn vocabulary, cyberspeak, network word and its lexical or textual analysis that networking is obtained in real time;Ancient books and records, poem, ancient Chinese prose, the translation of well-known saying;With
Family can be also keyed in into database from neologisms, the version of term or sentence created or quoted, these texts through verify or by
Confirm that after can use database can be added into.Same source text can be added a variety of different versions, and user can be to same source document
This different versions are evaluated, and collect optimal translation text as recommendation answer input database.
As shown in Figure 2, it is the flow of the invention based on database He the database formula interpretation method for being complementary to relation
Schematic diagram.Step 1 first:Receive the text for needing to translate.Reception mode is one of following:Website, mobile phone, phone, computer,
PDA.User is needed to input original language, source text, target language, input mode is divided into word input or phonetic entry, and voice is defeated
Enter to be converted to user with the text of phonetic representation and inputted after written form.
To step 2:Input after source text, each elementary cell carries out morphological analysis in system distich, record sentence
Length, parsing sentence structure, after go to step 3.
Step 3:Whether have completely available clause text, if any directly use if being retrieved in database.For example:From allusion quotation
In nationality, ancient Chinese prose, works, text of the identical in database has been determined, directly its version can have been regard as user
The translation result for inputting source text is presented.Corresponding text can not be directly obtained such as in database, then goes to step 4.
Step 4:The sub- elementary cell of distich carries out morphological analysis, record code pos and its all possible lexical or textual analysis, finds
The proper noun that can be matched and particular phrase lexical or textual analysis, can directly be applied mechanically.
Step 5:The matching lexical or textual analysis for whether having the basic text unit drawn from step 4 is retrieved from database, if any can
Directly apply mechanically, and go to step 6.
Step 6:Turned over using machine, word or expression lexical or textual analysis in text is retrieved from database, and determine the clause of target langua0
Framework.
Step 7:The lexical or textual analysis of word or expression is substituted into established target langua0 clause framework and forms version.
Step 8:Export translation result;Screen can be presented by the form of word in the version exported every time.
Step 9:Formed after result, decided whether to adopt by user, such as adopted, then as final result, go to step 15.Such as
It is not adopted, goes to step 10.
Step 10:In addition to machine turns over translation result, display that what is gathered from database, or from internet gather and source
The translation result of language text Similar Text is solved as reference, or by human translation.Go to step 11.
Step 11:If user is dissatisfied to three of the above translation result, problem can be suspended, anyone can input to be selected
Translation result, these results will occur when inquiring about for second as reference result.
Step 12:Form second of result.
Step 13:As a result it is adopted, then goes to step 14:It is not adopted and goes to step 5.
Step 14:As do not keyed in reference translation sheet, then can seek help internet true man's translation on line, form translation result, such as
It is adopted, goes to step 15, be not adopted, then go to step 5.
Step 15:The result as finally adopted by user, the result can be logged database, and typing content includes source language
Text and corresponding target langua0 text are sayed, makees inquiry next time and is used.Simultaneously reject database in it is identical with typing text and not by
The text adopted.
Step 16:Screen can be presented by the form of word in the version exported every time;Or it is translated into voice immediately
Mode is from audio output.
Step 17:By result, including:Primitive and the bilingual text or multilingual text of target language control, are stored in database,
Further to improve corpus data.Reject original text overlapping text and corpus data in database.
A kind of Database Interactive translation system of the present invention, the foundation of its translation system database and to improve be by miniature
Calculator software utilizes the advantage of internet on the platform for set up basic database, by being inputted by expert, on-line study, makes
The on-line automatic growth databases of method such as user evaluates, fan's support;Form multilingual, comprehensive, accurate practical automatic
Translation system.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all essences in the present invention
God is with principle, and any modification, equivalent substitution and improvements made etc. should be included in the scope of the protection.
Claims (3)
1. a kind of Database Interactive translation on line system, it is characterised in that including:
Online database, translating equipment;Wherein database is by including unit, memory cell, retrieval unit, matching unit, output
Unit is constituted;Translating equipment is defeated by receiver, discrimination unit, retrieval unit, type judging unit, display output unit, voice
Go out unit, evaluation unit, edit and record unit composition.
2. according to claim 1, online database, it is characterised in that including:
Include unit:By including from the word in internet, books, dictionary, sentence it is bilingual or it is multilingual control text set up
Basic database, and by constantly including newborn vocabulary and sentence, translation record is preserved come database of enriching constantly;Database pair
Same source text can include a variety of cypher texts (if having), and popular scoring is carried out to it determine that optimum answer is not classified as most preferably
The text of answer can be still retained, and database can show a variety of translation results in translation;It is open to include new text data, appoint
Who can all input new text to enrich database;The translation inputted for the public, database can be turned over to examine for method with machine and translated
Whether this originally corresponds in source;Database be based on Internet Construction, anyone anywhere, any country can supplementary data
Storehouse data;Memory cell:All words being included with various approach, sentence, text can all be stored on internet
In line database;Retrieval unit:The translation of anyone the source sheet that any language can be inputted into database and any language, number
Language can be carried out according to storehouse to classify and classified storage, so that abundant database;Any source text translated, can be directly from
Drawn in database, it is to avoid the syntax error being likely to occur when machine is turned over occur;To in ancient Chinese prose, poem, novel, science fiction works
Special word or sentence, directly from extracting existing bilingual or multilingual control translation or sample in database, it is to avoid to non-
Dictionary includes the situation that word or sentence can not be translated, or discourse structure of body can not caused by the special style of certain author
Problem analysis;Matching unit:Translated using stored data in database, it is direct from database to the text of existing translation
Extract;Output unit:The text that can be used through overmatching identification can be output to translating equipment.
3. according to claim 1, translating equipment, it is characterised in that including:
Receiver:Translation on line request for receiving user terminal transmission, the translation on line request is pre-configured in translation
In software, the translation on line request is sent in the case that owning user can not understand communication information;Discrimination unit:For
The languages of source language and target langua0 in translation on line request described in discrimination;Retrieval unit:Whether retrieved in database has matching can
With text, if any then can be used directly;Type judging unit:The unit that can not be retrieved from database, judges what is translated
Type is machine translation or human translation;Display output unit:From obtained by database retrieval, machine translation or human translation
The result of gained can show text output in the way of source language and target langua0 control;Voice-output unit:Data place is produced
Raw translation can both be expressed in the form of text mode presentation or by voice;Evaluation unit:User is carried out to translation result
Evaluate, evaluate optimal translation result;Edit and record unit:Database, which can classify, includes the mesh of the source language text translated every time and control
Chinese language sheet, do next time inquiry using.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710437862.4A CN107220243A (en) | 2017-05-31 | 2017-05-31 | A kind of Database Interactive translation system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710437862.4A CN107220243A (en) | 2017-05-31 | 2017-05-31 | A kind of Database Interactive translation system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107220243A true CN107220243A (en) | 2017-09-29 |
Family
ID=59947580
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710437862.4A Pending CN107220243A (en) | 2017-05-31 | 2017-05-31 | A kind of Database Interactive translation system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107220243A (en) |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107608978A (en) * | 2017-10-30 | 2018-01-19 | 华北水利水电大学 | A kind of inter-translation method of English and Russian |
CN108519979A (en) * | 2018-02-28 | 2018-09-11 | 成都优译信息技术股份有限公司 | The method and system that translation memory library and MT are combined in a kind of CAT systems |
CN109166594A (en) * | 2018-07-24 | 2019-01-08 | 北京搜狗科技发展有限公司 | A kind of data processing method, device and the device for data processing |
CN109408573A (en) * | 2018-10-11 | 2019-03-01 | 上海瀚银信息技术有限公司 | A kind of data collection system and collecting method of database |
CN109857696A (en) * | 2018-12-11 | 2019-06-07 | 西南石油大学 | The mutual auxiliary system of interconnection type multilingual information resource and its implementation method |
CN110866410A (en) * | 2019-11-15 | 2020-03-06 | 深圳市赛为智能股份有限公司 | Multi-language conversion method, device, computer equipment and storage medium |
CN110866408A (en) * | 2018-08-28 | 2020-03-06 | 本田技研工业株式会社 | Database creation device and search system |
CN111444678A (en) * | 2020-06-16 | 2020-07-24 | 四川大学 | Appeal information extraction method and system based on machine reading understanding |
CN112540682A (en) * | 2020-11-30 | 2021-03-23 | 山东智慧译百信息技术有限公司 | Intelligent translation input method based on machine translation result |
CN112784614A (en) * | 2021-03-03 | 2021-05-11 | 北京雅信诚医学信息科技有限公司 | Computer language translation system |
CN113191162A (en) * | 2021-04-21 | 2021-07-30 | 零壹人工智能科技研究院(南京)有限公司 | Medical translation system based on artificial intelligence AI translation |
CN115860015A (en) * | 2022-12-29 | 2023-03-28 | 北京中科智加科技有限公司 | Translation memory-based transcribed text translation method and computer equipment |
CN116070643A (en) * | 2023-04-03 | 2023-05-05 | 武昌理工学院 | Fixed style translation method and system from ancient text to English |
-
2017
- 2017-05-31 CN CN201710437862.4A patent/CN107220243A/en active Pending
Cited By (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107608978A (en) * | 2017-10-30 | 2018-01-19 | 华北水利水电大学 | A kind of inter-translation method of English and Russian |
CN108519979A (en) * | 2018-02-28 | 2018-09-11 | 成都优译信息技术股份有限公司 | The method and system that translation memory library and MT are combined in a kind of CAT systems |
CN109166594A (en) * | 2018-07-24 | 2019-01-08 | 北京搜狗科技发展有限公司 | A kind of data processing method, device and the device for data processing |
CN110866408A (en) * | 2018-08-28 | 2020-03-06 | 本田技研工业株式会社 | Database creation device and search system |
CN110866408B (en) * | 2018-08-28 | 2023-10-24 | 本田技研工业株式会社 | Database creation device and search system |
CN109408573A (en) * | 2018-10-11 | 2019-03-01 | 上海瀚银信息技术有限公司 | A kind of data collection system and collecting method of database |
CN109857696A (en) * | 2018-12-11 | 2019-06-07 | 西南石油大学 | The mutual auxiliary system of interconnection type multilingual information resource and its implementation method |
CN110866410B (en) * | 2019-11-15 | 2023-07-25 | 深圳市赛为智能股份有限公司 | Multilingual conversion method, multilingual conversion device, computer device, and storage medium |
CN110866410A (en) * | 2019-11-15 | 2020-03-06 | 深圳市赛为智能股份有限公司 | Multi-language conversion method, device, computer equipment and storage medium |
CN111444678A (en) * | 2020-06-16 | 2020-07-24 | 四川大学 | Appeal information extraction method and system based on machine reading understanding |
CN112540682A (en) * | 2020-11-30 | 2021-03-23 | 山东智慧译百信息技术有限公司 | Intelligent translation input method based on machine translation result |
CN112784614A (en) * | 2021-03-03 | 2021-05-11 | 北京雅信诚医学信息科技有限公司 | Computer language translation system |
CN113191162A (en) * | 2021-04-21 | 2021-07-30 | 零壹人工智能科技研究院(南京)有限公司 | Medical translation system based on artificial intelligence AI translation |
CN115860015A (en) * | 2022-12-29 | 2023-03-28 | 北京中科智加科技有限公司 | Translation memory-based transcribed text translation method and computer equipment |
CN116070643A (en) * | 2023-04-03 | 2023-05-05 | 武昌理工学院 | Fixed style translation method and system from ancient text to English |
CN116070643B (en) * | 2023-04-03 | 2023-08-15 | 武昌理工学院 | Fixed style translation method and system from ancient text to English |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107220243A (en) | A kind of Database Interactive translation system | |
CN109271529B (en) | Method for constructing bilingual knowledge graph of Xilier Mongolian and traditional Mongolian | |
KR100533810B1 (en) | Semi-Automatic Construction Method for Knowledge of Encyclopedia Question Answering System | |
KR101266361B1 (en) | Automatic translation system based on structured translation memory and automatic translating method using the same | |
CN103324621B (en) | A kind of Thai text spelling correcting method and device | |
CN103678684A (en) | Chinese word segmentation method based on navigation information retrieval | |
KR20150116675A (en) | Method and system for providing translated result | |
CN109949799B (en) | Semantic parsing method and system | |
CN107193798A (en) | A kind of examination question understanding method in rule-based examination question class automatically request-answering system | |
CN102214166A (en) | Machine translation system and machine translation method based on syntactic analysis and hierarchical model | |
Lamprinidis et al. | Universal joy a data set and results for classifying emotions across languages | |
CN105868187B (en) | The construction method of more translation Parallel Corpus | |
CN111046272A (en) | Intelligent question-answering system based on medical knowledge map | |
CN107133212A (en) | It is a kind of that recognition methods is contained based on integrated study and the text of words and phrases integrated information | |
CN114676255A (en) | Text processing method, device, equipment, storage medium and computer program product | |
CN106156013A (en) | The two-part machine translation method that a kind of regular collocation type phrase is preferential | |
CN108491399A (en) | Chinese to English machine translation method based on context iterative analysis | |
CN101763403A (en) | Query translation method facing multi-lingual information retrieval system | |
US10650195B2 (en) | Translated-clause generating method, translated-clause generating apparatus, and recording medium | |
CN103680503A (en) | Semantic identification method | |
CN104750676A (en) | Machine translation processing method and device | |
CN103164397A (en) | Chinese-Kazakh electronic dictionary and automatic translating Chinese- Kazakh method thereof | |
CN107894977A (en) | With reference to the Vietnamese part of speech labeling method of conversion of parts of speech part of speech disambiguation model and dictionary | |
CN103164398A (en) | Chinese-Uygur language electronic dictionary and automatic translating Chinese-Uygur language method thereof | |
KR101916781B1 (en) | Method and system for providing translated result |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170929 |