CN104090870B - A kind of method for pushing of translation on line engine - Google Patents
A kind of method for pushing of translation on line engine Download PDFInfo
- Publication number
- CN104090870B CN104090870B CN201410298485.7A CN201410298485A CN104090870B CN 104090870 B CN104090870 B CN 104090870B CN 201410298485 A CN201410298485 A CN 201410298485A CN 104090870 B CN104090870 B CN 104090870B
- Authority
- CN
- China
- Prior art keywords
- translation
- score value
- original text
- engine
- accounting
- 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.)
- Active
Links
Landscapes
- Machine Translation (AREA)
Abstract
A kind of method for pushing of translation on line engine, including:Obtain the waiting for translating sheet that user provides;Detect the ownership field of the waiting for translating sheet;Corresponding at least one translation engine is found in the mapping table of field and is pushed to user in the ownership field according to detecting.Waiting for translating sheet of the invention by analyzing user, determines the ownership field of waiting for translating sheet, transfers and be pushed to user in the strong translation engine of the translation ability to the ownership field, can effectively improve the efficiency of user's translation, and the accuracy of translation result.
Description
Technical field
The present invention relates to translation technology field, more particularly, to a kind of method for pushing of translation on line engine.
Background technology
At present, most people using translation service is translated by the translation engine provided on network, but now
Many companies are all proposed the translation engine under it, such as Baidu, Google, have, Kingsoft etc., for numerous translation engines
User can not know the quality of translation engine and stress high with the translation precision in which field, and user is for translation engine
Accept or reject, seriously affect the translation efficiency of user, and the accuracy of translation result.
The content of the invention
An object of the present invention is to provide a kind of method for pushing of translation on line engine, to solve user in the prior art
Use the problem of translation engine translation efficiency is low, accuracy is low.
In some illustrative embodiments, the method for pushing of the translation on line engine, including:Waiting for user's offer is provided
Translation sheet;Detect the ownership field of the waiting for translating sheet;The ownership field according to detecting is looked in the mapping table of field
User is pushed to corresponding at least one translation engine.
Compared with prior art, illustrative embodiment of the invention includes advantages below:
The unified standard analysis in ownership field is originally carried out by the waiting for translating to user, can find and be turned in the ownership field
Translate the high translation engine of precision and be pushed to user, user is greatly saved and is accepting or rejecting the time spent by translation engine, and protects
The accuracy of translation is demonstrate,proved.
Brief description of the drawings
Attached drawing described herein is used for providing a further understanding of the present invention, forms the part of the application, this hair
Bright schematic description and description is used to explain the present invention, does not form inappropriate limitation of the present invention.In the accompanying drawings:
Fig. 1 is the flow chart of illustrative embodiment according to the invention.
Embodiment
In the following detailed description, a large amount of specific details are proposed, in order to provide a thorough understanding of the present invention.But
It will be understood by those within the art that it can also implement the present invention even if without these specific details.In other cases, without detailed
Well-known method, process, component and circuit are carefully described, in order to avoid influence the understanding of the present invention.
Term " ownership field " used herein refers to the industry of content of text ownership, such as machinery, communication, chemical industry
Etc. industry;It is to determine that MT engine transfers phase in the database according to target language and ownership field in translation system
The corpus answered is translated.
Referring now to Fig. 1, Fig. 1 shows the flow chart according to the push in some illustrative embodiments.
As shown in Figure 1, in some illustrative embodiments, a kind of method for pushing of translation on line engine is disclosed, including:
S11, obtain the waiting for translating sheet that user provides;
S12, the ownership field for detecting the waiting for translating sheet;
Corresponding at least one translation engine is found in the mapping table of field in the ownership field that S13, basis detect
It is pushed to user.
The unified standard analysis in ownership field is originally carried out by the waiting for translating to user, can find and be turned in the ownership field
Translate the high translation engine of precision and be pushed to user, user is greatly saved and is accepting or rejecting the time spent by translation engine, and protects
The accuracy of translation is demonstrate,proved.
In some illustrative embodiments, the process in the ownership field of the waiting for translating sheet is detected, including:
To this progress of waiting for translating word segmentation processing, all terms in the waiting for translating sheet are obtained;Determine each described
The ownership field of term;Calculate accounting of the term in all terms in each ownership field;By returning for accounting maximum
Ownership field of the category field as the waiting for translating sheet.
Such as to waiting for translating this progress word segmentation processing after, obtain 20 terms wherein included, wherein, 10 terms are returned
Category field is communication, and the ownership field of 5 terms is machinery, and 5 terms are other field.Then the term accounting of the communications field is
10/20, the term accounting of machinery field is 5/20, and the term accounting summation of other field is 5/20, and the term of the communications field accounts for
Than maximum, i.e. the ownership field of waiting for translating sheet is the communications field.
In some illustrative embodiments, the differentiation of term is completed by term corpus, the terminology bank such as institute of table 1
Show;
Source languages | Target language | Industry is numbered | Former word | Translation |
EN | ZH-CN | The science of law is numbered | damages | Damages |
EN | ZH-CN | Literature is numbered | damages | Harm |
EN | ZH-CN | Physics is numbered | damages | Damage |
Table 1
In some illustrative embodiments, dictionary of the terminology bank as participle engine, during word segmentation processing, with art
Term in repertorie matches the term in text, the vocabulary obtained as word segmentation processing.
In some illustrative embodiments, correspondence is being found in the mapping table of field according to the ownership field detected
At least one translation engine be pushed to before user, further include:
The field mapping table is established, its process includes:
Each ownership field is handled as follows respectively:
Transfer reference original text and the reference translation under ownership field;
Word segmentation processing is carried out with reference to original text to described, obtains all terms therein;
All terms of acquisition are pushed to each translation engine respectively to be translated, and record translation result respectively;
Each translation result and the reference translation are subjected to term matching, and calculate each translation result successful match
Accounting of the term in all terms;
The accounting is established more than translation engine used in the translation result of threshold value and the incidence relation in the ownership field;
According to each ownership field, and the incidence relation, the field mapping table is built.Field mapping table such as table
Shown in 2;
Table 2
In some illustrative embodiments, found according to the ownership field detected in the mapping table of field corresponding
During multiple translation engines, further include:
The translation highest translation engine of score value is chosen in the multiple translation engine and is pushed to user.
Wherein, translation score value refer to by extracted using in a history translation database one translation document as survey
Try text, i.e., with reference to original text, and the reference translation with reference to original text.Reference translation is conventional professional interpreter's translation as a result, accurate
True property and reliability are all very high.
In some illustrative embodiments, the calculating process of the translation score value of each translation engine, including:
Transfer and refer to original text and reference translation;The reference original text is pushed to translation engine to be translated, record turns over
Translate result;One of following score value is at least calculated according to the translation result and the reference translation:Original text informativeness score value,
Discipline Maturity degree score value, information integrity score value and style of writing smoothness degree score value;Its summation is the translation score value of the translation engine.
Original text informativeness score value, Discipline Maturity degree score value, information integrity score value and style of writing smoothness degree score value are to translation
Score after the test of the relevant dimension of engine, by carrying out the test analysis of these dimensions to translation engine, the translation measured
The quality of engine is very reliable.
In some illustrative embodiments, original text informativeness refer to referenced text translated in translation engine after turn over
Translate the terminology match degree between result and reference translation.
In some illustrative embodiments, the process of the original text informativeness score value is calculated, including:
Word segmentation processing is carried out with reference to original text to described, obtains vocabulary therein;The vocabulary includes at least one below:One
First word, polynary word and common sentence;The vocabulary is pushed to translation engine to be translated, records translation result;Turned over described
Translate result to be matched with the reference translation, the successful vocabulary of record matching;The vocabulary of successful match is calculated in all vocabulary
In accounting;The obtained accounting is multiplied by original text informativeness weight coefficient, obtains the original text informativeness score value.
Wherein, unitary word refers to independent word, and the polynary phrase for referring to be made of at least two independent words, is fitted
Languages for similar English word structure;
In some illustrative embodiments, Discipline Maturity degree refer to referenced text translated in translation engine after turn over
Translate the term matching degree between result and reference translation.
In some illustrative embodiments, the process of the Discipline Maturity degree score value is calculated, including:
Word segmentation processing is carried out with reference to original text to described, obtains all terms;All terms are pushed to translation engine
Translated, record translation result;The translation result is matched with the reference translation, the successful art of record matching
Language;Calculate accounting of the term of successful match in all vocabulary;The obtained accounting is multiplied by Discipline Maturity degree weight system
Number, obtains the Discipline Maturity degree score value.
In some illustrative embodiments, information integrity refer to referenced text translated in translation engine after turn over
Translate the statement matching degree between result and reference translation.
In some illustrative embodiments, the process of described information integrity degree score value is calculated, including:
Determine all sentences with reference in original text;All sentences are pushed to translation engine to be translated, record turns over
Translate result;The translation result is matched with prime number reference translation, the successful sentence of record matching;Calculate successful match
Accounting of the sentence in all sentences;The obtained accounting is multiplied by information integrity weight coefficient, it is complete to obtain described information
Whole degree score value.
In some illustrative embodiments, style of writing smoothness degree refers to carry out in translation engine by that will find referenced text
The difference of word between translation result and reference translation or word after translation, the accounting in reference to original text.
In some illustrative embodiments, the process of the style of writing smoothness degree score value is calculated, including:
Translation engine will be pushed to reference to original text to be translated, record translation result;Translation result and the reference are translated
Text is matched, and counts the word or word of difference between the translation result and reference translation;The word or word for calculating the difference exist
The accounting with reference in original text;The obtained accounting is multiplied by style of writing smoothness degree weight coefficient, it is clear and coherent to obtain the style of writing
Spend score value.
At present, neither one unification, standard, rigorous method are gone back in the test for translation engine, calculate each translation
The score of engine, translation engine is pushed to by that will refer to original text, and translation result is analyzed compared with reference translation, is measured
Original text informativeness score value, Discipline Maturity degree score value, information integrity score value and the style of writing smoothness degree score value of translation engine, Ke Yishi
Now the test to translation engine is unified, and the effect that reliability is high.
The explanation of above example is only intended to help to understand method and its core concept of the invention;Meanwhile for this
The those skilled in the art in field, according to the thought of the present invention, there will be changes in specific embodiments and applications,
In conclusion this specification content should not be construed as limiting the invention.
Claims (8)
- A kind of 1. method for pushing of translation on line engine, it is characterised in that including:Obtain the waiting for translating sheet that user provides;Detect the ownership field of the waiting for translating sheet;Each ownership field is handled as follows respectively:Transfer reference original text and the reference translation under ownership field;Word segmentation processing is carried out with reference to original text to described, obtains all terms therein;All terms of acquisition are pushed to each translation engine respectively to be translated, and record translation result respectively;Each translation result and the reference translation are subjected to term matching, and calculate the term of each translation result successful match Accounting in all terms;The accounting is established more than translation engine used in the translation result of threshold value and the incidence relation in the ownership field;According to each ownership field, and the incidence relation, the field mapping table is built;Corresponding at least one translation engine is found in the mapping table of field and is pushed to use in the ownership field according to detecting Family.
- 2. method for pushing according to claim 1, it is characterised in that detect the mistake in the ownership field of the waiting for translating sheet Journey, including:To this progress of waiting for translating word segmentation processing, all terms in the waiting for translating sheet are obtained;Determine the ownership field of each term;Calculate accounting of the term in all terms in each ownership field;Ownership field using the maximum ownership field of the accounting as the waiting for translating sheet.
- 3. method for pushing according to claim 1, it is characterised in that the ownership field according to detecting is reflected in field When corresponding multiple translation engines are found in firing table, further include:The translation highest translation engine of score value is chosen in the multiple translation engine and is pushed to user.
- 4. method for pushing according to claim 3, it is characterised in that the calculating of the translation score value of each translation engine Process, including:Transfer and refer to original text and reference translation;The reference original text is pushed to translation engine to be translated, records translation result;One of following score value is at least calculated according to the translation result and the reference translation:Original text informativeness score value, art Language standard degree score value, information integrity score value and style of writing smoothness degree score value;Its summation is the translation score value of the translation engine.
- 5. method for pushing according to claim 4, it is characterised in that calculate the process of the original text informativeness score value, wrap Include:Word segmentation processing is carried out with reference to original text to described, obtains vocabulary therein;The vocabulary includes at least one below:Unitary Word, polynary word and common sentence;The vocabulary is pushed to translation engine to be translated, records translation result;The translation result is matched with the reference translation, the successful vocabulary of record matching;Calculate accounting of the vocabulary of successful match in all vocabulary;The obtained accounting is multiplied by original text informativeness weight coefficient, obtains the original text informativeness score value.
- 6. method for pushing according to claim 4, it is characterised in that calculate the process of the Discipline Maturity degree score value, wrap Include:Word segmentation processing is carried out with reference to original text to described, obtains all terms;All terms are pushed to translation engine to be translated, record translation result;The translation result is matched with the reference translation, the successful term of record matching;Calculate accounting of the term of successful match in all vocabulary;The obtained accounting is multiplied by Discipline Maturity degree weight coefficient, obtains the Discipline Maturity degree score value.
- 7. method for pushing according to claim 4, it is characterised in that calculate the process of described information integrity degree score value, bag Include:Determine all sentences with reference in original text;All sentences are pushed to translation engine to be translated, record translation result;The translation result is matched with prime number reference translation, the successful sentence of record matching;Calculate accounting of the sentence of successful match in all sentences;The obtained accounting is multiplied by information integrity weight coefficient, obtains described information integrity degree score value.
- 8. method for pushing according to claim 4, it is characterised in that calculate the process of the style of writing smoothness degree score value, bag Include:Translation engine will be pushed to reference to original text to be translated, record translation result;Translation result is matched with the reference translation, count between the translation result and reference translation the word of difference or Word;Calculate the difference word or word in the accounting with reference in original text;The obtained accounting is multiplied by style of writing smoothness degree weight coefficient, obtains the style of writing smoothness degree score value.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410298485.7A CN104090870B (en) | 2014-06-26 | 2014-06-26 | A kind of method for pushing of translation on line engine |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410298485.7A CN104090870B (en) | 2014-06-26 | 2014-06-26 | A kind of method for pushing of translation on line engine |
Publications (2)
Publication Number | Publication Date |
---|---|
CN104090870A CN104090870A (en) | 2014-10-08 |
CN104090870B true CN104090870B (en) | 2018-04-20 |
Family
ID=51638586
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410298485.7A Active CN104090870B (en) | 2014-06-26 | 2014-06-26 | A kind of method for pushing of translation on line engine |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104090870B (en) |
Families Citing this family (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104503960B (en) * | 2015-01-07 | 2017-09-19 | 渤海大学 | A kind of text data processing method for English Translation |
CN106021239B (en) * | 2016-04-29 | 2018-10-26 | 北京创鑫旅程网络技术有限公司 | A kind of translation quality real-time estimating method |
CN106777268A (en) * | 2016-12-28 | 2017-05-31 | 语联网(武汉)信息技术有限公司 | A kind of method of translation document storage and retrieval |
CN106874262A (en) * | 2017-01-09 | 2017-06-20 | 成都佳音多语信息技术有限公司 | A kind of statistical machine translation method for realizing domain-adaptive |
CN108228576B (en) * | 2017-12-29 | 2021-07-02 | 科大讯飞股份有限公司 | Text translation method and device |
CN108984540A (en) * | 2018-07-23 | 2018-12-11 | 传神语联网网络科技股份有限公司 | A kind of method and auxiliary translation system of supplementary translation |
CN109344408B (en) * | 2018-08-24 | 2022-02-18 | 腾讯科技(深圳)有限公司 | Translation detection method and device and electronic equipment |
CN109190132A (en) * | 2018-11-02 | 2019-01-11 | 语联网(武汉)信息技术有限公司 | Translation quality assessment method and device |
CN110472257A (en) * | 2019-08-20 | 2019-11-19 | 南京题麦壳斯信息科技有限公司 | A kind of MT engine assessment preferred method and system based on sentence pair |
CN111652006B (en) * | 2020-06-09 | 2021-02-09 | 北京中科凡语科技有限公司 | Computer-aided translation method and device |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6219646B1 (en) * | 1996-10-18 | 2001-04-17 | Gedanken Corp. | Methods and apparatus for translating between languages |
CN101388007A (en) * | 2007-09-14 | 2009-03-18 | 英业达股份有限公司 | Computer executed language translation system and method thereof |
CN102662935A (en) * | 2012-04-08 | 2012-09-12 | 北京语智云帆科技有限公司 | Interactive machine translation method and machine translation system |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN100474301C (en) * | 2005-09-08 | 2009-04-01 | 富士通株式会社 | System and method for obtaining words or phrases unit translation information based on data excavation |
-
2014
- 2014-06-26 CN CN201410298485.7A patent/CN104090870B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6219646B1 (en) * | 1996-10-18 | 2001-04-17 | Gedanken Corp. | Methods and apparatus for translating between languages |
CN101388007A (en) * | 2007-09-14 | 2009-03-18 | 英业达股份有限公司 | Computer executed language translation system and method thereof |
CN102662935A (en) * | 2012-04-08 | 2012-09-12 | 北京语智云帆科技有限公司 | Interactive machine translation method and machine translation system |
Also Published As
Publication number | Publication date |
---|---|
CN104090870A (en) | 2014-10-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104090870B (en) | A kind of method for pushing of translation on line engine | |
WO2018157805A1 (en) | Automatic questioning and answering processing method and automatic questioning and answering system | |
CN106997376B (en) | Question and answer sentence similarity calculation method based on multi-level features | |
KR101923650B1 (en) | System and Method for Sentence Embedding and Similar Question Retrieving | |
Gupta et al. | Mining Hindi-English Transliteration Pairs from Online Hindi Lyrics. | |
US20190188257A1 (en) | Context analysis apparatus and computer program therefor | |
CN109101489B (en) | Text automatic summarization method and device and electronic equipment | |
CN108052509A (en) | A kind of Text similarity computing method, apparatus and server | |
CN107577663A (en) | A kind of key-phrase extraction method and apparatus | |
CN103559313B (en) | Searching method and device | |
US20150134652A1 (en) | Method of extracting an important keyword and server performing the same | |
CN109213998A (en) | Chinese wrongly written character detection method and system | |
CN110929498A (en) | Short text similarity calculation method and device and readable storage medium | |
CN109344408A (en) | A kind of translation detection method, device and electronic equipment | |
CN105426379A (en) | Keyword weight calculation method based on position of word | |
CN117556050B (en) | Data classification and classification method and device, electronic equipment and storage medium | |
CN112395866B (en) | Customs clearance sheet data matching method and device | |
CN110580337A (en) | professional entity disambiguation implementation method based on entity similarity calculation | |
CN113642327A (en) | Method and device for constructing standard knowledge base | |
CN109766527B (en) | Text similarity calculation method and related equipment | |
Ahmad et al. | Pipilika n-gram viewer: an efficient large scale n-gram model for bengali | |
US10140289B2 (en) | Identifying propaganda in global social media | |
CN113408302B (en) | Evaluation method, device, equipment and storage medium of machine translation result | |
CN112395865B (en) | Check method and device for customs clearance sheet | |
CN112328757B (en) | Similar text retrieval method for question-answering system of business robot |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
CB02 | Change of applicant information | ||
CB02 | Change of applicant information |
Address after: 430070 East Lake Hubei Development Zone, Optics Valley Software Park, a phase of the west, South Lake Road South, Optics Valley Software Park, No. 2, No. 5, layer 205, six Applicant after: Language network (Wuhan) Information Technology Co., Ltd. Address before: 430073 East Lake Hubei Development Zone, Optics Valley Software Park, a phase of the west, South Lake Road South, Optics Valley Software Park, No. 2, No. 5, layer 205, six Applicant before: Wuhan Transn Information Technology Co., Ltd. |
|
GR01 | Patent grant | ||
GR01 | Patent grant |