CN106777268A - A kind of method of translation document storage and retrieval - Google Patents
A kind of method of translation document storage and retrieval Download PDFInfo
- Publication number
- CN106777268A CN106777268A CN201611237773.7A CN201611237773A CN106777268A CN 106777268 A CN106777268 A CN 106777268A CN 201611237773 A CN201611237773 A CN 201611237773A CN 106777268 A CN106777268 A CN 106777268A
- Authority
- CN
- China
- Prior art keywords
- translation
- manuscript
- matching
- sentence
- interpreter
- 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
- 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
- G06F16/3331—Query processing
- G06F16/3332—Query 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
- G06F16/338—Presentation of query results
-
- 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
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/211—Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
-
- 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
- G06F40/42—Data-driven translation
- G06F40/47—Machine-assisted translation, e.g. using translation memory
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Machine Translation (AREA)
Abstract
The present invention provides a kind of method of translation document storage and retrieval, it is characterized in that comprising the following steps:(1) manuscript of a translation storehouse, and feature tag are obtained;(2) sentence list is formed, language material alignment is carried out;(3) according to feature tag, classification storage is carried out to language material;(4) obtain and treat the manuscript of a translation, input inquiry label;(5) treating the manuscript of a translation carries out punctuate treatment, forms sentence list;(6) treat the manuscript of a translation and search argument is set, data retrieval, and language material matching are carried out in manuscript of a translation storehouse;(7) complete matching times and fuzzy matching number of times are recorded, is weighted;(8) result that retrieval is matched is obtained, is shown according to matching degree;Advantage is:Be conducive to quickly positioning the translation interpreter having experience in translation, and return to the translation reference documents of the interpreter, and cross sentence, term, the language material of former translation are returned into interpreter in the way of languages pair, be easy to interpreter to refer to, improve the translation efficiency of interpreter.
Description
Technical field
It is artificial intelligence the invention mainly relates to technical field, and in particular to a kind of side of translation document storage and retrieval
Method.
Background technology
Interpreter by after the completion of document translation, it is necessary to be stored to translation document, conventional store method is by not by file
Stored with bibliographic structure, document is classified by bibliographic structure, document of serving as interpreter increase, category of employment are increased
When, bibliographic structure will become extremely complex, very inconvenient during storage, it is also difficult to navigate to suitable storage catalogue at once immediately;
When needing to retrieve certain translation document, it is necessary to expend the very big time and manpower is looked for, and after finding translation document, also need
Reading documents content is wanted, common sentence therein, term, language material are found in document in artificial mode, be provided to translation
Personnel refer to and apply;This traditional mode storage efficiency is low, and storage organization is complicated, is unfavorable for that machine is stored and examined
Rope, and need substantial amounts of manpower to devote a tremendous amount of time when retrieving to be participated in, limited common sentence, term could be obtained
And language material.
The content of the invention
In order to solve the above technical problems, text analyzing is carried out to completed translation document the invention provides one kind, it is right
Sentence, term, language material are alignd, and are then classified by interpreter, languages, industry, by sentence to, term to, language material to entering
Row storage;When there is document to be translated, by document to be translated, affiliated industry documents to be translated, translation languages requirement input
System, carries out punctuate treatment to documents to be translated first, then goes in system to retrieve in sentence mode, can quickly retrieve translation
That crosses the sector and translation languages requirement has experience interpreter's information, and the interpreter related translation document, translated sentence,
Term, language material can according to the requirement of translation languages, by sentence to, term to, language material pair in the way of return to user.
The invention provides a kind of method of translation document storage and retrieval, it is characterized in that comprising the following steps:
Obtain manuscript of a translation storehouse, the manuscript of a translation storehouse includes some language materials and feature tag corresponding with language material, the language material include original text,
Translation corresponding with original text, the feature tag includes interpreter's information, languages, industry;
Punctuate treatment is carried out to the original text and translation in manuscript of a translation storehouse, sentence list is formed, the sentence list includes several sentences
Subelement;
Sentence unit in distich sublist carries out language material alignment;
According to feature tag, classification storage is carried out to language material;
The manuscript of a translation is treated in acquisition, and input inquiry label, the inquiry tag includes languages, industry;
Treating the manuscript of a translation carries out punctuate treatment, forms sentence list;
Treat the manuscript of a translation and search argument is set, the search argument includes sentence list, inquiry tag, with the search argument for treating the manuscript of a translation
Data retrieval, and language material matching are carried out in manuscript of a translation storehouse;
The matching includes matching and fuzzy matching completely;
Record the complete matching times of language material;
Record the fuzzy matching number of times of language material;
The weight coefficient of complete matching times and the weight coefficient of fuzzy matching number of times are set, by complete matching times with fuzzy
It is weighted with number of times;
Wherein, the weight coefficient of the complete matching times is described complete with the weight coefficient of fuzzy matching number of times and equal to 1
Weight coefficient of the weight coefficient of matching times more than fuzzy matching number of times;
The result that retrieval is matched is obtained, the retrieval result includes the interpreter's information, the corresponding manuscript of a translation of interpreter's information that match
The sentence list of original text and translation in storehouse and matching degree, show according to matching degree.
Further, the original text and translation in the storehouse to the manuscript of a translation carry out punctuate treatment, be original text and translation are converted into it is pure
Text message, and paragraph alignment is done, the paragraph after alignment is carried out into punctuate treatment.
Further, the manuscript of a translation for the treatment of carries out punctuate treatment, is that will treat that the manuscript of a translation is converted into plain text information, and do paragraph pair
Together, the paragraph after alignment is carried out into punctuate treatment.
Further, the fuzzy matching is:To treat that word segmentation processing is done in the sentence list of the manuscript of a translation, remove stop words and meaningless
Conjunction, preposition, the participle content of the sentence list for treating the manuscript of a translation is then done fuzzy with the sentence unit of translation in manuscript of a translation storehouse
Matching, sentence number of the statistics similarity more than 50%.
Further, the weight coefficient of the weight coefficient and fuzzy matching number of times for setting complete matching times, is basis
Empirical value is configured.
Further, the empirical value of the weight coefficient of the complete matching times is 70%, the weighting of the fuzzy matching number of times
The empirical value of coefficient is 30%.
The beneficial effects of the invention are as follows:
1st, the classification to translation document is stored, there is provided storage efficiency, is easy to document to store positioning;
2nd, the original text and translation to translation document carry out text analyzing, do sentence alignment treatment, and a sentence as one to depositing
Storage unit, is conducive to by Sentence Search;
3rd, system storage mode reduces manpower participation, has saved human cost and time cost;
4th, submit the interpreter's information retrieved, can quickly return to correlation experience documents to be translated to, be easy to the positioning of interpreter,
The cost of interpreter is looked in reduction by manpower;
5th, the translated reference documents of interpreter are returned, is easy to submit to the interpreter and is referred to, improve the translation efficiency of interpreter;
6th, the sentence that matches completely is returned to, term to, language material pair, is easy to submit to the interpreter and is referred to, improve interpreter's
Translation efficiency;
7th, the sentence of fuzzy matching is returned to, term to, language material pair, is easy to submit to the interpreter and is referred to, improve interpreter's
Translation efficiency.
The present invention provides text analyzing to completed translation document, by interpreter, languages, trade classification, and languages
To storage mode;System matches are carried out to documents to be translated, is conducive to quickly positioning the translation interpreter having experience in translation, and
The translation reference documents of the interpreter are returned, and cross sentence, term, the language material of former translation are returned in the way of languages pair
Interpreter, is easy to interpreter to refer to, and improves the translation efficiency of interpreter.
Brief description of the drawings
Accompanying drawing described herein is used for providing a further understanding of the present invention, constitutes the part of the application, this hair
Bright schematic description and description does not constitute inappropriate limitation of the present invention, in the accompanying drawings for explaining the present invention:
Fig. 1 is schematic diagram of the invention.
Specific embodiment
Technical scheme is further described in detail with reference to the accompanying drawings and detailed description.
As shown in figure 1, the present invention provides a kind of method of translation document storage and retrieval, comprise the following steps:
(1)Manuscript of a translation storehouse is obtained, the manuscript of a translation storehouse includes some language materials and feature tag corresponding with language material, and the language material includes original
Text translation corresponding with original text, the feature tag includes interpreter's information, languages, industry;
Comprise the concrete steps that:
a)Upload completed translation document, including the original text and translation for having completed translation document;
b)It is input into interpreter's information of completed translation document, translation languages requirement, affiliated trade information.
(2)Original text in manuscript of a translation storehouse and translation paragraph are alignd, punctuate treatment will be carried out to paragraph thereafter, form sentence
List, the sentence list includes several sentence units;Sentence unit in distich sublist carries out language material alignment;
Comprise the concrete steps that:
a)The original text and translation that translation document will have been completed are converted into plain text information;
The paragraph alignment of original text and translation is carried out first, to the treatment of paragraph punctuate, forms sentence list;
B) sentence, term, language material alignment and then by the sentence unit in sentence list are carried out.
(3)According to feature tag, classification storage is carried out to language material;
Comprise the concrete steps that:To having completed translation document classification storage is carried out by interpreter, languages, industry etc..
(4)The manuscript of a translation is treated in acquisition, and input inquiry label, the inquiry tag includes languages, industry;
Comprise the concrete steps that:
A) document to be translated is uploaded;
B) interpreter's information documents to be translated, the requirement of translation languages, affiliated trade information are input into.
(5)Treating the manuscript of a translation carries out punctuate treatment, forms sentence list;Comprise the concrete steps that:
A) will treat that the manuscript of a translation is converted into plain text information;
The paragraph alignment of the manuscript of a translation will be treated first, punctuate treatment is carried out to the paragraph after alignment, form sentence list;
B) sentence, term, language material alignment and then by the sentence unit in sentence list are carried out.
(6)Treat the manuscript of a translation and search argument is set, the search argument includes sentence list, inquiry tag, with treating the manuscript of a translation
Search argument carries out data retrieval, and language material matching in manuscript of a translation storehouse.
(7)Record and calculate matching degree
The matching includes matching and fuzzy matching completely;
Record the complete matching times of language material;
Record the fuzzy matching number of times of language material;
The weight coefficient of complete matching times and the weight coefficient of fuzzy matching number of times are set, by complete matching times with fuzzy
It is weighted with number of times;
Wherein, the weight coefficient of the complete matching times is described complete with the weight coefficient of fuzzy matching number of times and equal to 1
Weight coefficient of the weight coefficient of matching times more than fuzzy matching number of times;
Comprise the concrete steps that:
A) obtain the interpreter requires the translation document list of completion with affiliated industry in the languages, and document is pressed in the document list
Matching degree be ranked up, the matching degree document ranking higher of document is more forward;
B) calculating of the matching degree of document includes two statistics of part of the complete matching times of sentence and fuzzy matching number of times;
C) the complete matching times of sentence are recorded:Sentence documents to be translated is the same in the original text for completed translation document
Occur once, complete matching times just add 1;
D) the fuzzy matching number of times of sentence is recorded:Sentence documents to be translated is done into word segmentation processing, removes stop words and meaningless
Conjunction, preposition, then the participle of the sentence and completed the sentence list of translation document and singly done fuzzy
Match somebody with somebody, sentence number of the statistics similarity more than 50%;
E) the matching degree score of document is calculated:The complete matching times of sentence and fuzzy matching number of times weighted statistical are drawn, it is complete
The weight coefficient of full matching times is empirically worth and is set to 70%, and the weight coefficient of fuzzy matching number of times is empirically worth setting
It is 30%;
F) returned the matching degree of document as the parameter of document.
(8)The result that retrieval is matched is obtained, the retrieval result includes the interpreter's information, the interpreter's information correspondence that match
Manuscript of a translation storehouse in original text and translation sentence list and matching degree, shown according to matching degree;
Comprise the concrete steps that:
A) sentence that matches completely is obtained to, term to, language material pair, returns to interpreter;
b)The sentence of fuzzy matching is obtained to, term to, language material pair, interpreter is returned to.
It should be noted last that, above specific embodiment is merely illustrative of the technical solution of the present invention and unrestricted,
Although being described in detail to the present invention with reference to preferred embodiment, it will be understood by those within the art that, can be right
Technical scheme is modified or equivalent, and without deviating from the spirit and scope of technical solution of the present invention, its is equal
Should cover in the middle of scope of the presently claimed invention.
Claims (6)
1. a kind of method of translation document storage and retrieval, it is characterized in that comprising the following steps:
Obtain manuscript of a translation storehouse, the manuscript of a translation storehouse includes some language materials and feature tag corresponding with language material, the language material include original text,
Translation corresponding with original text, the feature tag includes interpreter's information, languages, industry;
Punctuate treatment is carried out to the original text and translation in manuscript of a translation storehouse, sentence list is formed, the sentence list includes several sentences
Subelement;
Sentence unit in distich sublist carries out language material alignment;
According to feature tag, classification storage is carried out to language material;
The manuscript of a translation is treated in acquisition, and input inquiry label, the inquiry tag includes languages, industry;
Treating the manuscript of a translation carries out punctuate treatment, forms sentence list;
Treat the manuscript of a translation and search argument is set, the search argument includes sentence list, inquiry tag, with the search argument for treating the manuscript of a translation
Data retrieval, and language material matching are carried out in manuscript of a translation storehouse;
The matching includes matching and fuzzy matching completely;
Record the complete matching times of language material;
Record the fuzzy matching number of times of language material;
The weight coefficient of complete matching times and the weight coefficient of fuzzy matching number of times are set, by complete matching times with fuzzy
It is weighted with number of times;
Wherein, the weight coefficient of the complete matching times is described complete with the weight coefficient of fuzzy matching number of times and equal to 1
Weight coefficient of the weight coefficient of matching times more than fuzzy matching number of times;
The result that retrieval is matched is obtained, the retrieval result includes the interpreter's information, the corresponding manuscript of a translation of interpreter's information that match
The sentence list of original text and translation in storehouse and matching degree, show according to matching degree.
2. the method for a kind of translation document storage and retrieval according to claim 1, it is characterized in that in the storehouse to the manuscript of a translation
Original text and translation carry out punctuate treatment, be that original text and translation are converted into plain text information, and do paragraph alignment, after alignment
Paragraph carry out punctuate treatment.
3. the method for a kind of translation document storage and retrieval according to claim 1, it is characterized in that the manuscript of a translation for the treatment of enters
The treatment of row punctuate, is that will treat that the manuscript of a translation is converted into plain text information, and does paragraph alignment, and the paragraph after alignment is carried out at punctuate
Reason.
4. the method for a kind of translation document storage and retrieval according to claim 1, it is characterized in that the fuzzy matching is:
To treat that word segmentation processing is done in the sentence list of the manuscript of a translation, remove stop words and insignificant conjunction, preposition, then the sentence for treating the manuscript of a translation
The participle content of sublist does fuzzy matching, the statistics similarity sentence more than 50% with the sentence unit of translation in manuscript of a translation storehouse
Number.
5. the method for a kind of translation document storage and retrieval according to claim 1, it is characterized in that described set complete
The weight coefficient of weight coefficient and fuzzy matching number of times with number of times, is to be configured based on experience value.
6. the method for a kind of translation document storage and retrieval according to claim 5, matches time completely it is characterized in that described
The empirical value of several weight coefficients is 70%, and the empirical value of the weight coefficient of the fuzzy matching number of times is 30%.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611237773.7A CN106777268A (en) | 2016-12-28 | 2016-12-28 | A kind of method of translation document storage and retrieval |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611237773.7A CN106777268A (en) | 2016-12-28 | 2016-12-28 | A kind of method of translation document storage and retrieval |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106777268A true CN106777268A (en) | 2017-05-31 |
Family
ID=58924984
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611237773.7A Pending CN106777268A (en) | 2016-12-28 | 2016-12-28 | A kind of method of translation document storage and retrieval |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106777268A (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107590140A (en) * | 2017-10-17 | 2018-01-16 | 语联网(武汉)信息技术有限公司 | Entry process method is translated in a kind of document leakage |
CN107741931A (en) * | 2017-08-30 | 2018-02-27 | 捷开通讯(深圳)有限公司 | Interpretation method, mobile terminal and the storage device of operating system framework |
CN110532451A (en) * | 2019-06-26 | 2019-12-03 | 平安科技(深圳)有限公司 | Search method and device for policy text, storage medium, electronic device |
CN110837742A (en) * | 2019-11-15 | 2020-02-25 | 广州市汇泉翻译服务有限公司 | Man-machine combined translation batch processing translation method containing artificial intelligence |
CN111191469A (en) * | 2019-12-17 | 2020-05-22 | 语联网(武汉)信息技术有限公司 | Large-scale corpus cleaning and aligning method and device |
CN112052334A (en) * | 2020-09-02 | 2020-12-08 | 广州极天信息技术股份有限公司 | Text paraphrasing method, text paraphrasing device and storage medium |
CN112766003A (en) * | 2021-01-20 | 2021-05-07 | 语联网(武汉)信息技术有限公司 | Document auxiliary translation method and device |
WO2022224057A1 (en) * | 2021-04-20 | 2022-10-27 | Deeptranslate Limited | Machine translation guided by reference documents |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103823796A (en) * | 2014-02-25 | 2014-05-28 | 武汉传神信息技术有限公司 | System and method for translation |
CN104090870A (en) * | 2014-06-26 | 2014-10-08 | 武汉传神信息技术有限公司 | Pushing method of online translation engines |
CN104360996A (en) * | 2014-11-27 | 2015-02-18 | 武汉传神信息技术有限公司 | Sentence alignment method of bilingual text |
CN105446962A (en) * | 2015-12-30 | 2016-03-30 | 武汉传神信息技术有限公司 | Original text and translated text alignment method and apparatus |
-
2016
- 2016-12-28 CN CN201611237773.7A patent/CN106777268A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103823796A (en) * | 2014-02-25 | 2014-05-28 | 武汉传神信息技术有限公司 | System and method for translation |
CN104090870A (en) * | 2014-06-26 | 2014-10-08 | 武汉传神信息技术有限公司 | Pushing method of online translation engines |
CN104360996A (en) * | 2014-11-27 | 2015-02-18 | 武汉传神信息技术有限公司 | Sentence alignment method of bilingual text |
CN105446962A (en) * | 2015-12-30 | 2016-03-30 | 武汉传神信息技术有限公司 | Original text and translated text alignment method and apparatus |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107741931A (en) * | 2017-08-30 | 2018-02-27 | 捷开通讯(深圳)有限公司 | Interpretation method, mobile terminal and the storage device of operating system framework |
CN107590140A (en) * | 2017-10-17 | 2018-01-16 | 语联网(武汉)信息技术有限公司 | Entry process method is translated in a kind of document leakage |
CN107590140B (en) * | 2017-10-17 | 2020-09-25 | 语联网(武汉)信息技术有限公司 | Document missing item processing method |
CN110532451A (en) * | 2019-06-26 | 2019-12-03 | 平安科技(深圳)有限公司 | Search method and device for policy text, storage medium, electronic device |
CN110532451B (en) * | 2019-06-26 | 2023-08-29 | 平安科技(深圳)有限公司 | Method and device for searching policy text, storage medium and electronic device |
CN110837742A (en) * | 2019-11-15 | 2020-02-25 | 广州市汇泉翻译服务有限公司 | Man-machine combined translation batch processing translation method containing artificial intelligence |
CN111191469A (en) * | 2019-12-17 | 2020-05-22 | 语联网(武汉)信息技术有限公司 | Large-scale corpus cleaning and aligning method and device |
CN111191469B (en) * | 2019-12-17 | 2023-09-19 | 语联网(武汉)信息技术有限公司 | Large-scale corpus cleaning and aligning method and device |
CN112052334A (en) * | 2020-09-02 | 2020-12-08 | 广州极天信息技术股份有限公司 | Text paraphrasing method, text paraphrasing device and storage medium |
CN112052334B (en) * | 2020-09-02 | 2024-04-05 | 广州极天信息技术股份有限公司 | Text interpretation method, device and storage medium |
CN112766003A (en) * | 2021-01-20 | 2021-05-07 | 语联网(武汉)信息技术有限公司 | Document auxiliary translation method and device |
WO2022224057A1 (en) * | 2021-04-20 | 2022-10-27 | Deeptranslate Limited | Machine translation guided by reference documents |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106777268A (en) | A kind of method of translation document storage and retrieval | |
CN105279495B (en) | A kind of video presentation method summarized based on deep learning and text | |
WO2018010365A1 (en) | Cross-media search method | |
CN110472047B (en) | Multi-feature fusion Chinese-Yue news viewpoint sentence extraction method | |
CN109299480A (en) | Terminology Translation method and device based on context of co-text | |
CN107895000B (en) | Cross-domain semantic information retrieval method based on convolutional neural network | |
CN103559193B (en) | A kind of based on the theme modeling method selecting unit | |
CN110931128B (en) | Method, system and device for automatically identifying unsupervised symptoms of unstructured medical texts | |
Wang et al. | Efficientclip: Efficient cross-modal pre-training by ensemble confident learning and language modeling | |
CN113076411B (en) | Medical query expansion method based on knowledge graph | |
CN108509521A (en) | A kind of image search method automatically generating text index | |
CN105677795A (en) | Abstract semantics recommendation method, recommendation device and recommendation system | |
CN112100212A (en) | Case scenario extraction method based on machine learning and rule matching | |
CN111563372B (en) | Typesetting document content self-duplication checking method based on teaching book publishing | |
CN106570120A (en) | Process for realizing searching engine optimization through improved keyword optimization | |
Aung et al. | Personality prediction based on content of Facebook users: A literature review | |
CN112530584A (en) | Medical diagnosis assisting method and system | |
CN114997181A (en) | Intelligent question-answering method and system based on user feedback correction | |
CN116049422A (en) | Echinococcosis knowledge graph construction method based on combined extraction model and application thereof | |
Janaki Raman et al. | Automatic text summarization of article (NEWS) using lexical chains and wordnet—A review | |
CN110347812A (en) | A kind of search ordering method and system towards judicial style | |
CN112084312B (en) | Intelligent customer service system constructed based on knowledge graph | |
CN112949293A (en) | Similar text generation method, similar text generation device and intelligent equipment | |
CN110209765B (en) | Method and device for searching keywords according to meanings | |
CN112115256A (en) | Method and device for generating news text abstract integrated with Chinese stroke information |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170531 |
|
RJ01 | Rejection of invention patent application after publication |