CN109871546A - A kind of patent document translation system - Google Patents
A kind of patent document translation system Download PDFInfo
- Publication number
- CN109871546A CN109871546A CN201711249574.2A CN201711249574A CN109871546A CN 109871546 A CN109871546 A CN 109871546A CN 201711249574 A CN201711249574 A CN 201711249574A CN 109871546 A CN109871546 A CN 109871546A
- Authority
- CN
- China
- Prior art keywords
- translated
- patent document
- translation
- module
- sentence
- 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
Landscapes
- Machine Translation (AREA)
Abstract
The present invention relates to a kind of patent document translation systems comprising input module, preprocessing module, database module, message processing module and display module, input module are used to receive the source language data of patent document to be translated；Preprocessing module extracts keyword message based on the patent document to be translated of input and keyword message is inputted keyword setting unit；Database module is searched from patent database based on keyword message and patent document to be translated is close or part is close and possesses an at least document for object language document of the same clan as a reference, and creates reference statement library according to bibliography；Message processing module is searched to paragraph to be translated matching or relevant sentence in reference statement library to record, and is shown the data record of original text sentence and comparison translation sentence in display area identical with translation by display module.Patent document translation system provided by the invention has accuracy high, and efficiency is fast, advantage applied widely.
Description
Technical field
The present invention relates to machine translation mothod more particularly to a kind of patent document translation systems.
Background technique
With popularizing for Internet, the computer disposal of natural language becomes obtains the important of knowledge from internet
Means.For example, in the fields such as international exchange and scientific research and education, people need to translate foreign country's spoken and written languages, and the past, this was
The stage that great master of linguistics displays one's talent.It with the rapid development of computer technology and constantly improve, machine translation obtains increasingly
It is widely applied.Machine translation has own big advantage, and if translation speed is fast, memory capability is strong, while can also reduce and turn over
It is translated into etc., but the disadvantage is that translation quality is also far from satisfying the demand of people at present, how to develop the machine of high quality
Device interpretation method becomes urgent problem to be solved.
The characteristics of having its own due to the document in different technologies field, current general machine translation are difficult to use in all
Technical field.It is both technological document and legal document to patent document, accuracy and preciseness is required in translation, it is right
Its translation quality has higher requirement, thus patent translator mostly uses greatly the mode of manual translation every words.Translator
Although can be translated based on application of the same clan, there is still a need for first retrieving to related patents, related text is selected by hand,
This mode not only low efficiency, and error probability is higher.The characteristics of patent document is write due to it, there are more in document
The usual phrase of patent, in application number, applicant, abstract, claims, specification, technical field, background technique, invention
Appearance, specific embodiment etc.；There is also more fixation and common sentence form of presentation in patent document, such as described
..., the present invention provides one kind ... method, provided by the invention ... at least there is following advantage, the claim of this patent
Range is ... etc.；There is also a large amount of high frequency vocabulary in patent application document, the term meeting such as occurred in detail in the claims
Repeatedly occur in summary of the invention, specific embodiment.Due to the These characteristics of patent document, so that patent document can in translation
The information of reference is more.
These characteristics based on patent document, the Chinese patent application of Publication No. CN103488627A, disclose one kind
Full piece patent document interpretation method and translation system.The translation system that the patent provides is obtained by carrying out morphological analysis to full text
At object language and wrong identification and amendment are carried out to translation result to phrase, then by the phrase translation；It is right in full text translation
The noun phrase is directly replaced using revised result；After the completion of translation, by original text title Sequential output.Although the patent energy
It enough obtains in patent document and commonly uses complicated noun phrase, reduce the analysis time of the sentence containing common complicated noun phrase, mention
High translation speed, still, there is also following defects for the patent:
(1) range of the patent file collection selected by is wide, and specific aim is not strong, in this, as the reference translation of phrase to be translated,
It is easy to cause the mistranslation of technical term；
(2) to the translation of full text, the translation of only phrase have passed through amendment, and sentence is the translation provided using the patent
System is directly translated, not high to the accuracy of sentence translation；
(3) patent is only applicable to the translation of patent application document, to notice, notice turn text etc. other with patent phase
The document of pass is simultaneously not suitable for；
(4) this method does not fully consider in patent document and has in the Translation characteristics of proper noun and patent documentation data library
There is more the characteristics of can refer to information.
Most of all, the interpretation method that the patent provides, which mainly passes through, extracts patent file concentration and phrase to be translated
Corresponding high frequency phrases are not tied as reference translation, method of this merely selection high frequency phrases translation as reference translation
The semanteme of phrase in the patent literature is closed, it is similar with common translation software, it is be easy to cause the mistranslation of phrase, is especially easy to make
At the mistranslation of technical term, so that the translation of patent document loses preciseness and professional feature.
Summary of the invention
It is an object of the invention to overcome the deficiencies of the prior art and provide a kind of patent document translation system, the translations
System includes input module, preprocessing module, database module, message processing module and display module, and the input module is used
In the source language data for receiving patent document to be translated；The preprocessing module is extracted based on the patent document to be translated of input and is closed
The keyword message is simultaneously inputted keyword setting unit by key word information；The database module is based on the keyword message
It is searched from patent database close with the patent document to be translated and possesses at least one of object language document of the same clan
Document as a reference, and creates reference statement library as follows: by the database module with single punctuation mark
Document will be compared for separator and splits into single reference original text sentence, and is stored in the reference with reference to original text sentence for described
In statement library, meanwhile, the database module splits into reference translation document individually using single punctuation mark as separator
Reference translation sentence, and by the reference translation sentence according to it is described with reference to original text sentence one by one corresponding mode be stored in
In the reference statement library；The message processing module is searched and the matched sentence of paragraph to be translated in the reference statement library
The matched sentence supplies record display in display area identical with translation to record, and by display module
Translator's reference and/or editor.
According to a preferred embodiment, the database module is based on the keyword message from patent database
It cannot find out close with the patent document to be translated and possess an at least document conduct for object language document of the same clan
When bibliography, the keyword message based on the patent document to be translated is searched close with the patent document part to be translated
Bibliography and form reference statement library, searched in the reference statement library by the message processing module with it is described to
The translation matched sentence of paragraph translates at least part content of the patent document to be translated to after record, and is based on
Feature after translation carries out Auto-matching in the patent database of object language, to search and the patent document to be translated
Relevant documents.
According to a preferred embodiment, the message processing module cannot be found out in the reference statement library with
When the matched sentence of paragraph to be translated is to record, by the message processing module in the reference statement as unit of syntagma
Relevant to paragraph to be translated sentence is searched in library to record, and by the display module by the data of the correlative pair
Record, which is shown in display area identical with translation, to be referred to and/or is edited for translator.
According to a preferred embodiment, the preprocessing module further includes weight coefficient setting unit, the weight
Coefficient setting unit assigns different weights to it based on the primary and secondary sequence of the keyword message for translator respectively, makes
The database module can be searched according to the weight information it is close or part is close with the patent document to be translated
Bibliography.
According to a preferred embodiment, the preprocessing module further includes high frequency vocabulary setting unit, translator
According to the length of patent document to be translated by the threshold value that the high frequency vocabulary setting unit is arranged extract it is described it is to be translated specially
High frequency vocabulary in sharp document, the threshold value are 10 or more.
Specific embodiment
Technical solution of the present invention is detailed further below, but protection scope of the present invention is not limited to following institute
It states.
Embodiment:
A kind of patent document translation system, the translation system include input module, preprocessing module, database module,
Message processing module and display module, the input module are used to receive the source language data of patent document to be translated；It is described pre-
Processing module extracts keyword message based on the patent document to be translated of input and sets keyword message input keyword
Set unit；The database module is based on the keyword message and searches from patent database and the patent document to be translated
An at least document that is close and possessing object language document of the same clan as a reference, and creates refer to language as follows
Sentence library: single reference original text language is split by document is compared using single punctuation mark as separator by the database module
Sentence, and be stored in described in the reference statement library with reference to original text sentence, meanwhile, the database module is with single punctuate
Symbol is that reference translation document is split into single reference translation sentence by separator, and by the reference translation sentence according to
It is described that with reference to original text sentence, corresponding mode is stored in the reference statement library one by one；The message processing module is in the ginseng
Examine in statement library search with the matched sentence of paragraph to be translated to record, and by display module by the matched sentence to note
Record, which is shown in display area identical with translation, to refer to and/or is edited for translator.Preferably, single punctuate symbol
Number be comma, branch, colon or fullstop.It is highly preferred that single punctuation mark is fullstop.Preferably, with it is described to be translated
The matched sentence of paragraph to be recorded as it is described with reference to original text sentence and the identical sentence of paragraph to be translated to record.
Preferably, the database module be based on the keyword message cannot be found out from patent database with it is described
When patent document to be translated approaches and possesses an at least document for object language document of the same clan as a reference, it is based on institute
The keyword message for stating patent document to be translated is searched and the close bibliography in the patent document part to be translated and formation
Reference statement library is searched in the reference statement library and the matched language of paragraph to be translated by the message processing module
At least part content of the patent document to be translated is translated after sentence pair record, and based on the feature after translation in mesh
Auto-matching is carried out in the patent database of poster speech, to search documents relevant to the patent document to be translated.
It is preferably based on pith or main portion of the sentence in the reference statement library to record to the patent document to be translated
Divide and is translated.Preferably, with the close bibliography of the patent document to be translated be the bibliography with described wait turn over
Translate the correlation that patent document has 50% or more.Preferably, the bibliography close with the patent document part to be translated
Claims, background technique or specification etc. for the bibliography and the patent document to be translated have 20% or more
Correlation.
Preferably, the message processing module cannot be found out and the paragraph to be translated in the reference statement library
The sentence matched to record when, by the message processing module as unit of syntagma in the reference statement library search with it is described to
The relevant sentence of paragraph is translated to record, and by the display module by the data record of the correlative pair show with
It refers to and/or edits for translator in the identical display area of translation.Preferably, by the message processing module in institute
State in reference statement library search with the paragraph to be translated have 30% and the above correlation sentence to record, and pass through show mould
Block by the data record of the correlative pair show in display area identical with translation for translator refer to and/
Or editor.It is highly preferred that being searched in the reference statement library by the message processing module has with the paragraph to be translated
50% and the above correlation sentence to record, and by display module by the data record of the correlative pair show with
It refers to and/or edits for translator in the identical display area of translation.Preferably, the message processing module is based on institute
State sentence in paragraph to be translated and the reference statement library the consecutive identical text of record is determined the paragraph to be translated with
Correlation of the sentence to record.
Preferably, the preprocessing module further includes weight coefficient setting unit, and the weight coefficient setting unit is used for
Translator assigns different weights to it based on the primary and secondary sequence of the keyword message respectively, so that the database module
It can be according to the bibliography that weight information lookup is approached with the patent document to be translated or part is close.
Preferably, the preprocessing module further includes high frequency vocabulary setting unit, and translator is according to patent text to be translated
The length offered extracts the high frequency words in the patent document to be translated by the threshold value that the high frequency vocabulary setting unit is arranged
It converges, the threshold value is 10 or more.
Preferably, the suggestion translation of the high frequency vocabulary is by the message processing module based on to the reference statement library
It analyzes and provides, shown sentence related with translation is suggested record identical with translation by the display module
It refers to and/or edits for translator in display area, after the translation of the high frequency vocabulary determines, the patent document translation
System replaces the high frequency vocabulary in all paragraphs to be translated automatically.Preferably, translator is based on and the suggestion translation
Related sentence translates the auxiliary of record to high frequency vocabulary, hereafter, then by translator based on related with translation is suggested
Sentence the auxiliary of record translates paragraph to be translated relevant to high frequency vocabulary.Finally, system is based on high frequency vocabulary
The translation of paragraph to be translated relevant with to high frequency vocabulary to being replaced in full.
Preferably, before the patent document translation to be translated, the message processing module is literary by the patent to be translated
It offers and splits into single paragraph to be translated so that the message processing module can be with institute by separator of single punctuation mark
Stating single paragraph to be translated is that unit is searched and the paragraph matching to be translated or relevant language in the reference statement library
Sentence pair record.Preferably, single punctuation mark is comma, branch, colon or fullstop.It is highly preferred that single punctuate accords with
Number be comma.Preferably, when translating claims, the locating function of module based on information processing, to summary of the invention and tool
The related translation of body embodiment part is shown by editor side in a synchronous manner understands that right is wanted with supplementary translation personnel
The obscure text in book is sought, to reduce mistranslation.
Preferably, it when completing the translation of each paragraph to be translated, is translated by the message processing module with completed
Literary automatic replacement and the current identical paragraph to be translated of paragraph to be translated, meanwhile, after being replaced by the display module
Paragraph to be translated mark so as to translator confirmation.Preferably, the display module is with the color and/or word different from original text
Body adjusts text to indicate replaced word segment so that translator can be based on actual conditions.
Preferably, when completing full text translation, it is described to be translated that syntactic analysis extraction is based on by the message processing module
The high frequency vocabulary and/or high frequency term of major part are searched and the high frequency vocabulary as after keyword in full text in patent document
And/or the relevant sentence record of high frequency term, and shown by the display module in the same window so as to translator's energy
Enough check the consistency that the high frequency vocabulary and/or high frequency term are translated in context.If it was found that context translation is inconsistent
It is automatically complete using message processing module or when needing to adjust the high frequency vocabulary and/or high frequency term in translation process
The related mistranslation field of text replacement.Preferably, display module is to the secondary modified high frequency vocabulary and/or high frequency term with not
Color and/or the font of original text are same as to indicate replaced word segment so that translator can adjust based on actual conditions
Text.
The present invention also provides the method using patent document translation system translation patent document of the invention, the translations
The method of patent document includes the following steps: before starting translation, inputs the source language data of patent document to be translated, defeated based on
The source language data entered extracts keyword message and assigns different weights respectively to it, meanwhile, the threshold value of high frequency vocabulary is set；
It searches close with the patent document to be translated by the database module and possesses object language document of the same clan at least
One document creates reference statement library as a reference and as follows: will compare by separator of single punctuation mark
Document splits into single reference original text sentence, and is stored in described in the reference statement library with reference to original text sentence, meanwhile,
Reference translation document is split into single reference translation sentence by separator of single punctuation mark by the database module,
And by the reference translation sentence according to corresponding mode is stored in the reference statement library one by one with the reference original text sentence
In, and the message processing module splits into the patent document to be translated individually using single punctuation mark as separator
Paragraph to be translated.
When starting translation, translator determines institute based on the suggestion translation for the high frequency vocabulary that the message processing module provides
State the accurate translation of high frequency vocabulary；Hereafter, translator being provided with the paragraph to be translated based on the message processing module
Matching or relevant sentence determine the translation of the paragraph to be translated to record, and the patent document translation system will be translated with described
The identical paragraph to be translated of original text of text is directly replaced by the translation；Alternatively, cannot be looked by the database module
An at least document that is close with the patent document to be translated and possessing object language document of the same clan is found out to be used as with reference to text
When offering, the patent document translation system based on the patent document to be translated keyword message search with it is described it is to be translated specially
Sharp literature department taps close bibliography and forms reference statement library, and translator is based on the reference statement library can be to described
At least part content of patent document to be translated translated and according to the feature after translation object language patent data
Auto-matching is carried out in library, to search documents relevant to the patent document to be translated；Preferably, translator's base
The auxiliary of record translates high frequency vocabulary in sentence related with the suggestion translation, hereafter, then by translator's base
The auxiliary of record translates paragraph to be translated relevant with high frequency vocabulary in sentence related to suggestion translation, finally,
Translation of the system based on high frequency vocabulary and paragraph to be translated relevant to high frequency vocabulary to being replaced in full.
The high frequency vocabulary extracted when completing full text translation based on the message processing module and/or high frequency term conduct
Keyword checks the consistency that the high frequency vocabulary and/or high frequency term are translated in context.
Patent document translation system of the invention creates reference according to the bibliography found in patent database
Statement library is searched record relevant to paragraph to be translated from the reference statement library and is referred to for translator, due to bibliography
Patent document is also belonged to, translation equally has the characteristics that accuracy and preciseness, thus translation matter can be improved using the system
Amount, edits the reference translation provided in addition, translator can be combined with itself L proficiency, can further improve and turn over
The accuracy translated.
Patent document translation system of the invention using single punctuation mark as separator by bibliography and it is to be translated specially
Sharp file declustering is supplied to the ginseng of translator at single reference statement and paragraph to be translated, so fractionation mode, system
It is stronger compared with bigger and reference information the specific aim of information content for extracting phrase merely in the prior art to examine information content, translator
The translation matter of patent document can be improved according to the understanding to reference translation sentence pair with the accurate translation of determination paragraph to be translated
Amount；And the present invention carries out searching as unit of syntagma correlative to record, the similarity of search result and syntagma to be translated
It is high.
Patent document translation system of the invention can directly replace each automatically after the translation for determining high frequency vocabulary and wait for
Translate corresponding high frequency vocabulary in paragraph, meanwhile, every translation finishes a paragraph to be translated, translation can be applied to automatically and its
The characteristics of identical paragraph to be translated, which takes full advantage of patent document itself, translation speed can be improved.
For that can not be retrieved in patent database close with patent document to be translated and to possess object language of the same clan
An at least document for document as a reference when, patent document translation system of the invention additionally provides a kind of rough translation
The method of patent document can greatly save translation cost and time.
A specific embodiment of the invention above described embodiment only expresses, the description thereof is more specific and detailed, but simultaneously
Limitations on the scope of the patent of the present invention therefore cannot be interpreted as.It should be pointed out that for those of ordinary skill in the art
For, without departing from the inventive concept of the premise, various modifications and improvements can be made, these belong to guarantor of the invention
Protect range.
Claims (5)
1. a kind of patent document translation system, the translation system includes input module, preprocessing module, database module, letter
Cease processing module and display module, which is characterized in that the input module is used to receive the original language number of patent document to be translated
According to；
To be translated patent document extraction keyword message of the preprocessing module based on input is simultaneously defeated by the keyword message
Entry keyword setting unit；
The database module is searched from patent database based on the keyword message and is connect with the patent document to be translated
An at least document that is close and possessing object language document of the same clan as a reference, and creates reference statement as follows
Library: single reference original text language is split by document is compared using single punctuation mark as separator by the database module
Sentence, and be stored in described in the reference statement library with reference to original text sentence, meanwhile, the database module is with single punctuate
Symbol is that reference translation document is split into single reference translation sentence by separator, and by the reference translation sentence according to
It is described that with reference to original text sentence, corresponding mode is stored in the reference statement library one by one；
The message processing module is searched with the matched sentence of paragraph to be translated in the reference statement library to record, and is passed through
Display module refers to the matched sentence to record display in display area identical with translation for translator
And/or editor.
2. patent document translation system as described in claim 1, which is characterized in that the database module is based on the key
Word information cannot find out close with the patent document to be translated from patent database and possess object language text of the same clan
At least document offered as a reference when, keyword message based on the patent document to be translated search with it is described to
The translation close bibliography in patent document part simultaneously forms reference statement library, by the message processing module in the reference
In statement library search with the matched sentence of paragraph to be translated to after record at least one of the patent document to be translated
Point content is translated, and Auto-matching is carried out in the patent database of object language based on the feature after translation, to look into
Look for documents relevant to the patent document to be translated.
3. patent document translation system as claimed in claim 1 or 2, which is characterized in that the message processing module is described
Cannot be found out in reference statement library with the matched sentence of paragraph to be translated to record when, by the message processing module with
Syntagma is that unit searches sentence relevant to paragraph to be translated to record in the reference statement library, and passes through the display mould
Block by the data record of the correlative pair show in display area identical with translation for translator refer to and/
Or editor.
4. patent document translation system as described in claim 1, which is characterized in that the preprocessing module further includes weight system
Number setting unit, the weight coefficient setting unit is for translator based on the primary and secondary sequence of the keyword message to its point
Different weights is not assigned, and the database module is searched and the patent text to be translated according to the weight information
Offer close or close part bibliography.
5. patent document translation system as claimed in claim 4, which is characterized in that the preprocessing module further includes high frequency words
Remittance setting unit, the threshold value that translator is arranged according to the length of patent document to be translated by the high frequency vocabulary setting unit
And the high frequency vocabulary in the patent document to be translated is extracted, the threshold value is 10 or more.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711249574.2A CN109871546A (en) | 2017-12-01 | 2017-12-01 | A kind of patent document translation system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711249574.2A CN109871546A (en) | 2017-12-01 | 2017-12-01 | A kind of patent document translation system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109871546A true CN109871546A (en) | 2019-06-11 |
Family
ID=66913551
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711249574.2A Pending CN109871546A (en) | 2017-12-01 | 2017-12-01 | A kind of patent document translation system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109871546A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110543641A (en) * | 2019-08-14 | 2019-12-06 | 交控科技股份有限公司 | chinese and foreign language information comparison method and device |
| CN110728156A (en) * | 2019-12-19 | 2020-01-24 | 北京百度网讯科技有限公司 | Translation method and device, electronic equipment and readable storage medium |
| CN111737992A (en) * | 2020-07-06 | 2020-10-02 | 和宇健康科技股份有限公司 | Three-way text information processing method, computer equipment and storage medium |
| CN114139554A (en) * | 2021-11-23 | 2022-03-04 | 成都飞机工业（集团）有限责任公司 | Translation method based on fuzzy query system for computer translation |
| WO2022224057A1 (en) * | 2021-04-20 | 2022-10-27 | Deeptranslate Limited | Machine translation guided by reference documents |
-
2017
- 2017-12-01 CN CN201711249574.2A patent/CN109871546A/en active Pending
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110543641A (en) * | 2019-08-14 | 2019-12-06 | 交控科技股份有限公司 | chinese and foreign language information comparison method and device |
| CN110543641B (en) * | 2019-08-14 | 2023-05-26 | 交控科技股份有限公司 | Chinese and foreign language information comparison method and device |
| CN110728156A (en) * | 2019-12-19 | 2020-01-24 | 北京百度网讯科技有限公司 | Translation method and device, electronic equipment and readable storage medium |
| US11574135B2 (en) | 2019-12-19 | 2023-02-07 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Method, apparatus, electronic device and readable storage medium for translation |
| CN111737992A (en) * | 2020-07-06 | 2020-10-02 | 和宇健康科技股份有限公司 | Three-way text information processing method, computer equipment and storage medium |
| CN111737992B (en) * | 2020-07-06 | 2020-12-22 | 和宇健康科技股份有限公司 | Three-way text information processing method, computer equipment and storage medium |
| WO2022224057A1 (en) * | 2021-04-20 | 2022-10-27 | Deeptranslate Limited | Machine translation guided by reference documents |
| CN114139554A (en) * | 2021-11-23 | 2022-03-04 | 成都飞机工业（集团）有限责任公司 | Translation method based on fuzzy query system for computer translation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109871546A (en) | A kind of patent document translation system | |
| Gutierrez-Vasques et al. | Axolotl: a web accessible parallel corpus for Spanish-Nahuatl | |
| CN104408078A (en) | Construction method for key word-based Chinese-English bilingual parallel corpora | |
| Alansary et al. | Building an International Corpus of Arabic (ICA): progress of compilation stage | |
| Tachicart et al. | Building a Moroccan dialect electronic dictionary (MDED) | |
| Rivera et al. | A flexible framework for collocation retrieval and translation from parallel and comparable corpora | |
| Aswani et al. | A hybrid approach to align sentences and words in English-Hindi parallel corpora | |
| CN109871548A (en) | A kind of patent document interpretation method | |
| Lo et al. | Cool English: A grammatical error correction system based on large learner corpora | |
| Raupova | Principles of creating an electronic dictionary of grammatical terms | |
| CN103164398A (en) | Chinese-Uygur language electronic dictionary and automatic translating Chinese-Uygur language method thereof | |
| Shvedova et al. | Handling of nonstandard spelling in GRAC | |
| Feng | Evolution and present situation of corpus research in China | |
| Rajitha et al. | Sinhala and english document alignment using statistical machine translation | |
| Goweder et al. | Identifying broken plurals in unvowelised arabic tex | |
| Rosmorduc | Computational linguistics in egyptology | |
| Sankaravelayuthan et al. | English to tamil machine translation system using parallel corpus | |
| Sellam et al. | Improved Statistical Machine Translation by Cross-Lingustic Projection of Named Entities Recognition and Translation | |
| Zhao | Research on English translation skills and problems by using computer technology | |
| Atwell | Classical and modern Arabic corpora | |
| Anderson et al. | SIG | |
| Parvez | Named entity recognition from bengali newspaper data | |
| May et al. | Surprise! What's in a Cebuano or Hindi Name? | |
| Meurant et al. | Modelling a parallel corpus of french and french belgian sign language | |
| Devi et al. | Advancements on NLP applications for Manipuri language |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190611 |
|
| WD01 | Invention patent application deemed withdrawn after publication |