CN107885728A - A kind of QA automatic testing methods and system based on interpreter's translation on line - Google Patents
A kind of QA automatic testing methods and system based on interpreter's translation on line Download PDFInfo
- Publication number
- CN107885728A CN107885728A CN201711310624.3A CN201711310624A CN107885728A CN 107885728 A CN107885728 A CN 107885728A CN 201711310624 A CN201711310624 A CN 201711310624A CN 107885728 A CN107885728 A CN 107885728A
- Authority
- CN
- China
- Prior art keywords
- translation
- syntagma
- original text
- interpreter
- line
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/226—Validation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/232—Orthographic correction, e.g. spell checking or vowelisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/40—Processing or translation of natural language
- G06F40/58—Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Machine Translation (AREA)
Abstract
The invention belongs to language processing techniques field, disclose a kind of QA automatic testing methods and system based on interpreter's translation on line, according to project original text and translation translation, whether sequence detection Arabic numerals match, sequence detection whether leaky translation, in sequence detection context, sequence detection whether there is translation syntax error, and institute is according to project original text and translation translation, if Terminology Translation mistake be present, and syntagma position, syntagma original text, syntagma translation and error message are write in QA examining reports.The present invention is during interpreter translates, QA detections to translation quality are all intelligent, interpreter can be at any time according to selection, QA detections are carried out to translation, and be modified according to examining report, it substituted in the prior art, cumbersome time-consuming artificial QA detections, the efficiency of QA detections is greatly improved, has ensured the quality of translation.
Description
Technical field
The invention belongs to language processing techniques field, more particularly to a kind of QA automatic detection sides based on interpreter's translation on line
Method and system.
Background technology
Along with flourishing for translation industry, translation software and instrument are also greatly developed.Area of computer aided is turned over
Translate (Computer Aided Translation, CAT) software systems can help translator it is high-quality, it is efficient, easily complete
Translation.In general translation project is according to translating, examine and revise, the flow of quality inspection, be accomplished manually the task of each node.Interpreter
In the translation of translation, due to the hand reason such as by mistake, there can be some low wrong phenomenons, such as punctuate, grammer, situations such as being translated one more, this
Class mistake is all by manually examining and revising or finding when quality inspection, modification at present；For this low mistake, by manually examining
School and the mode of quality inspection, it is not easy to be found, especially expend time and the energy of interpreter.
The content of the invention
The problem of existing for prior art, the invention provides a kind of QA automatic detection sides based on interpreter's translation on line
Method and system.
The present invention is achieved in that a kind of QA automatic testing methods based on interpreter's translation on line, and the method will can translate
The literary online progress automatic quality inspections of QA, come out being investigated in the low wrong short time present in translation, are presented to interpreter and modify, QA
Automatic quality inspection content is Arabic numerals inspection, leakage is translated, translated one more, syntax error, term detect etc..
Based on syntagma information based on online original text and translation, the automatic quality inspections of QA are according to the contents of a project for selecting to check
Checked, the process of each single item quality inspection is as follows：
Arabic numerals inspection：Calling regular expression Pattern ("\\d+(\\.\\d+)*") matcher methods,
To original text syntagma carry out Arabic numerals retrieval, if Arabic numerals in original text be present, matching retrieval translation in whether
There are Arabic numerals, if there is no then recording；If there is carrying out comparison of coherence judgement, if than if more consistent by,
Recorded if less consistent.
Inspection is translated in leakage：Translation syntagma is checked with the presence or absence of be sky or be null character string situation, if there is then recording.
Being translated one more：Statistics original text repeats syntagma and records specific line number, to be translated corresponding to first repetition syntagma of original text
On the basis of sentence section, compare translation syntagma one by one, when finding the inconsistent situation of translation, then record；In such a manner by whole sentences
Section is disposed, and records corresponding error message.
Grammer detects：By calling the LanguageTool services of increasing income, according to language, syntax rule, sentence by sentence section examined
Survey, sentence that translation syntagma contains syntax error, position, error reason information are returned and recorded.
Term detects：Based on existing terminology bank, detect in original text syntagma whether contain art by way of matching
Language, if contained, detect in translation syntagma whether use translation vocabulary corresponding to term, if it is not, record.
The error result information of whole quality inspection items record, collect as report, prompt interpreter to modify translation.
QA automatic testing methods provided by the invention based on interpreter's translation on line, during interpreter translates, paginal translation
The QA detections of literary quality are all intelligent, and interpreter can carry out QA detections at any time according to selection to translation, and according to examining report
Be modified, substituted in the prior art it is cumbersome it is time-consuming it is artificial examine and revise, quality inspection links.
By using the automatic quality detecting methods of QA online, can be interpreter examine and revise and quality inspection improve 60% efficiency, than artificial
Quality inspection and the time for examining and revising saving 2/3rds.
Detection method is translated one more, being ensured with there is a situation where to translate one in 100% exclusion translation one before and after translation more
Cause, even if multiple person cooperational is translated, translation effect is also exactly the same, hence it is evident that improves translation quality.
Term detection method, ensure in the translation project of multiple person cooperational, term use obtains unification, and meeting project will
Ask.
Grammer detection, leakage is translated and Arabic numerals detection method, can exclude low mistake with 100%, is saved than hand inspection
2/3rds time.
Brief description of the drawings
Fig. 1 is the QA automatic testing method flow charts provided in an embodiment of the present invention based on interpreter's translation on line.
Fig. 2 is the QA detecting system schematic devices provided in an embodiment of the present invention based on interpreter's translation on line.
In figure：1st, Arabic numerals detection verifying unit；2nd, leakage translation detection means；3rd, context consistency detection fills
Put；4th, syntax error detection means；5th, term error detector element.
Embodiment
In order to make the purpose , technical scheme and advantage of the present invention be clearer, with reference to embodiments, to the present invention
It is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not used to
Limit the present invention.
CAT software categories are various at present, and while being offered convenience to interpreter, there is also some problems.Such as in document
When holding more, leaky translation easily occurs；When the translation time is longer, situations such as context translation is inconsistent easily occurs；It is not yet done
The translation of proper noun is inaccurate, inconsistent etc. in the field known, and these problems cause interpreter to translate the horizontal ginseng of the translation come
Difference is uneven, and translation quality can not obtain effective guarantee.
The application principle of the present invention is explained in detail below in conjunction with the accompanying drawings.
It is provided in an embodiment of the present invention based on the QA automatic testing methods of interpreter's translation on line interpreter translate during,
QA detections to translation quality are all intelligent, and interpreter can carry out QA detections at any time according to selection to translation, and according to detection
Report is modified, and substituted in the prior art, cumbersome time-consuming artificial QA detections, is greatly improved the effect of QA detections
Rate, the quality of translation is ensured.
Specifically include：
According to project original text and translation translation, whether sequence detection Arabic numerals match, and syntagma position, syntagma is former
Text, syntagma translation and error message write-in QA examining reports；
According to project original text and translation translation, sequence detection whether leaky translation, and by syntagma position, syntagma original text, sentence
Duan Yiwen and error message write-in QA examining reports；
According to project original text and translation is translated, in sequence detection context, if exist and translate inconsistent syntagma, and will
Syntagma position, syntagma original text, syntagma translation and error message write-in QA examining reports；
According to project original text and translation translation, sequence detection whether there is translation syntax error, and by syntagma position, syntagma
Original text, syntagma translation and error message write-in QA examining reports；
Institute is according to project original text and translation translation, if Terminology Translation mistake be present, and by syntagma position, syntagma original text,
Syntagma translation and error message write-in QA examining reports.
As shown in figure 1, the QA automatic testing methods provided in an embodiment of the present invention based on interpreter's translation on line are including following
Step：
S101：Interpreter opens translation duties by network；
S102：Interpreter carries out QA detections, and Arabic numerals, leakage translation, context translation uniformity, grammer can be selected wrong
The QA classifications such as mistake, term mistake；
S103：The QA classifications that QA detecting systems select according to interpreter, QA detections are carried out to the translation of translation on line；
S104：QA detecting systems generate QA examining reports according to testing result；
S105：Interpreter checks QA examining reports and entry by network online, is changed one by one online or ignores processing.
In S102, S103, if interpreter selects【Arabic numerals】Classification, QA detecting systems are then by calling canonical table
Up to formula Pattern ("\\d+(\\.\\d+)*") matcher methods, carry out original text Arabic numerals retrieval, one by one with translating
Text is matched, and is thought to translate if translation has matched identical Arabic numerals successfully, is otherwise identified as category defect, puts
Enter in QA testing results；
In S102, S103, if interpreter selects【Leakage translation】Classification, QA detecting systems then start to retrieve original text, are every
Individual translation unit search corresponding to translation state, (unit translated and confirmed can be identified as completion), do not identify for the category
Defect, it is put into QA testing results；
In S102, S103, if interpreter selects【Context is inconsistent】Classification, QA detecting systems start to retrieve in original text
Identical translation unit, (translation unit is completely the same including punctuation mark), if identical unit be present, is examined
Whether the translation for surveying these units is identical.Use in the invention and be defined by occurring the translation result of the translation unit for the first time, its
Translation in its identical translation unit occurs inconsistent with first time, then labeled as category defect, is put into QA detection knots
In fruit；
In S102, S103, if interpreter selects【Syntax error】The sentence of translation is spliced into by classification, QA detecting systems
Long paragraph, it is sent to LanguageTool services (LanguageTool is a style and syntactic correction software), the service
According to language, syntax rule is loaded, is detected sentence by sentence, and each sentence, position, error reason for having syntax error are believed
Breath returns to QA detecting systems, and system judges corresponding errors present, content, type further according to result, and is labeled as category defect,
It is put into QA testing results；
In S102, S103, if interpreter selects【Term mistake】Classification, QA detecting systems according to the terminology bank of carry,
One by one retrieval original text whether there is corresponding term, if it does, detection translate it is whether consistent, unanimously then by, it is inconsistent, mark
Category defect is designated as, is put into QA testing results.
As shown in Fig. 2 the embodiment of the present invention also provides a kind of QA detecting systems based on interpreter's translation on line, the system
Including:Arabic numerals detection verifying unit 1, leakage translation detection means 2, context consistency detection device 3, syntax error inspection
Survey device 4, term error detector element 5.
The Arabic numerals detect verifying unit 1, for Arabic according to project original text and translation translation, sequence detection
Whether numeral is matched, and syntagma position, syntagma original text, syntagma translation and defect information are write into QA examining reports；
It is described leakage translation detection means 2, for according to project original text with translation translation, sequence detection whether leaky translation,
And syntagma position, syntagma original text, syntagma translation and information are write into QA examining reports；
The context consistency detection device 3, for according to project original text and translation translation, sequence detection context
In, if exist and translate inconsistent syntagma, and syntagma position, syntagma original text, syntagma translation and information write-in QA are examined
Observe and predict announcement；
The syntax error detection means 4, for whether there is translation according to project original text and translation translation, sequence detection
Syntax error, and syntagma position, syntagma original text, syntagma translation and information are write into QA examining reports；
The term error detector element 5, for according to project original text and translation translation, if Terminology Translation mistake be present
By mistake, and by syntagma position, syntagma original text, syntagma translation and information QA examining reports are write；
The Arabic numerals detect verifying unit 1, by call regular expression Pattern ("\\d+(\\.\\d +)*") matcher methods, carry out original text Arabic numerals retrieval, matched one by one with translation, if translation has matched
Identical Arabic numerals are then thought to translate successfully, are otherwise identified as category defect, are put into QA testing results；
The leakage translation detection means 2 retrieves original text since original position, to be translated corresponding to the lookup of each translation unit
Literary state, (unit translated and confirmed can be identified as completion), do not identify for category defect, be put into QA testing results；
The context consistency detection device 3, identical translation unit in original text is retrieved since original position, (should
Translation unit is completely the same including punctuation mark), if identical unit be present, detecting the translation of these units is
It is no identical.Use in the invention and be defined by occurring the translation result of the translation unit for the first time, in other identical translation units
Translation with first time occur it is inconsistent, then labeled as category defect, be put into QA testing results；
The syntax error detection means 4, by the whole paragraph of sentence splicing growth of translation, it is sent to LanguageTool clothes
It is engaged in (LanguageTool is a style and syntactic correction software), the service loads syntax rule, carried out sentence by sentence according to language
Detection, and each sentence, position, error reason information for having syntax error are returned to QA detecting systems, system is further according to knot
Fruit judges corresponding errors present, content, type, and is labeled as category defect, is put into QA testing results；
The term error detector element 5, according to the terminology bank of carry, original text is retrieved one by one and whether there is corresponding term,
If it does, detection translation it is whether consistent, unanimously then by, it is inconsistent to be then labeled as category defect, be put into QA testing results
In.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all essences in the present invention
All any modification, equivalent and improvement made within refreshing and principle etc., should be included in the scope of the protection.
Claims (8)
1. a kind of QA automatic testing methods based on interpreter's translation on line, it is characterised in that described based on interpreter's translation on line
During QA automatic testing methods are translated, all intellectualities are detected to the QA of translation quality, at any time according to selection, translation entered
Row QA is detected, and is modified according to examining report.
2. the QA automatic testing methods based on interpreter's translation on line as claimed in claim 1, it is characterised in that described to be based on translating
The QA detection methods of member's translation on line specifically include：
According to project original text and translation translation, whether sequence detection Arabic numerals match, and by syntagma position, syntagma original text,
Syntagma translation and error message write-in QA examining reports；
According to project original text and translation translation, sequence detection whether leaky translation, and syntagma position, syntagma original text, syntagma are translated
Text and error message write-in QA examining reports；
According to project original text and translation translation, in sequence detection context, if exist and translate inconsistent syntagma, and by syntagma
Position, syntagma original text, syntagma translation and error message write-in QA examining reports；
According to project original text and translation translation, sequence detection whether there is translation syntax error, and syntagma position, syntagma is former
Text, syntagma translation and error message write-in QA examining reports；
Institute is according to project original text and translation translation, if Terminology Translation mistake be present, and by syntagma position, syntagma original text, syntagma
Translation and error message write-in QA examining reports.
3. a kind of QA automatic testing methods based on interpreter's translation on line as claimed in claim 1 based on interpreter's translation on line
QA automatic checkout systems, it is characterised in that the QA automatic checkout systems based on interpreter's translation on line include:
Arabic numerals detect verifying unit, for according to project original text and translation translation, whether sequence detection Arabic numerals
Matching, and syntagma position, syntagma original text, syntagma translation and error message are write into QA examining reports；
Leakage translation detection means, for according to project original text and translation translation, sequence detection whether leaky translation, and by syntagma position
Put, syntagma original text, syntagma translation and error message write-in QA examining reports；
Context consistency detection device, for according to project original text and translation translation, in sequence detection context, if exist
Inconsistent syntagma is translated, and syntagma position, syntagma original text, syntagma translation and error message are write into QA examining reports；
Syntax error detection means, for whether there is translation syntax error according to project original text and translation translation, sequence detection,
And syntagma position, syntagma original text, syntagma translation and error message are write into QA examining reports；
Term error detector element, for according to project original text and translation translation, if Terminology Translation mistake be present, and by syntagma
Position, syntagma original text, syntagma translation and error message write-in QA examining reports.
4. the QA automatic checkout systems based on interpreter's translation on line as claimed in claim 3, it is characterised in that the Arab
Digital Detecting verifying unit, by calling regular expression Pattern matcher methods, carry out original text Arabic numerals
Retrieval, is matched with translation, thinks to translate successfully if translation has matched identical Arabic numerals, be otherwise identified as one by one
Category defect, it is put into QA testing results.
5. the QA automatic checkout systems based on interpreter's translation on line as claimed in claim 3, it is characterised in that the leakage translation
Detection means retrieves original text since original position, and for translation state corresponding to the lookup of each translation unit, what is do not identified is to be somebody's turn to do
Classification defect, it is put into QA testing results.
6. the QA automatic checkout systems based on interpreter's translation on line as claimed in claim 3, it is characterised in that the context
Consistency detection device, identical translation unit in original text is retrieved since original position, if identical unit be present, is detected
Whether the translation of these units is identical；Use in the invention and be defined by occurring the translation result of the translation unit for the first time, it is other
Translation in identical translation unit occurs inconsistent with first time, then labeled as category defect, is put into QA testing results
In.
7. the QA automatic checkout systems based on interpreter's translation on line as claimed in claim 3, it is characterised in that the grammer is wrong
Error detection device, the splicing of the sentence of translation is grown up whole paragraph, is sent to LanguageTool services, the service according to language,
Syntax rule is loaded, is detected sentence by sentence, and each sentence, position, error reason information for having syntax error are returned to QA
Detecting system, system judges corresponding errors present, content, type further according to result, and is labeled as category defect, is put into QA inspections
Survey in result.
8. the QA automatic checkout systems based on interpreter's translation on line as claimed in claim 3, it is characterised in that the term is wrong
Error detection device, according to the terminology bank of carry, original text is retrieved one by one and whether there is corresponding term, if it does, detection translation is
It is no consistent, unanimously then by, it is inconsistent to be then labeled as category defect, be put into QA testing results.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711310624.3A CN107885728A (en) | 2017-12-11 | 2017-12-11 | A kind of QA automatic testing methods and system based on interpreter's translation on line |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711310624.3A CN107885728A (en) | 2017-12-11 | 2017-12-11 | A kind of QA automatic testing methods and system based on interpreter's translation on line |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107885728A true CN107885728A (en) | 2018-04-06 |
Family
ID=61773457
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711310624.3A Pending CN107885728A (en) | 2017-12-11 | 2017-12-11 | A kind of QA automatic testing methods and system based on interpreter's translation on line |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107885728A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108984525A (en) * | 2018-07-06 | 2018-12-11 | 北京邮电大学 | A kind of Chinese grammer error-detecting method based on the term vector that text information is added |
| CN109359306A (en) * | 2018-10-16 | 2019-02-19 | 传神语联网网络科技股份有限公司 | Translation bearing calibration and system based on reiterant sentences detection |
| CN109522563A (en) * | 2018-10-15 | 2019-03-26 | 语联网（武汉）信息技术有限公司 | Judge automatically the method and device that statement translation finishes |
| 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 |
| CN111191440A (en) * | 2019-12-13 | 2020-05-22 | 语联网（武汉）信息技术有限公司 | Method and system for measuring word error correction for translated text in translation |
| CN112036136A (en) * | 2020-09-01 | 2020-12-04 | 文思海辉智科科技有限公司 | Quality inspection data processing method and device, electronic equipment and readable storage medium |
| CN112215015A (en) * | 2020-09-02 | 2021-01-12 | 文思海辉智科科技有限公司 | Translation text revision method, translation text revision device, computer equipment and storage medium |
| CN113743101A (en) * | 2021-08-17 | 2021-12-03 | 北京百度网讯科技有限公司 | Text error correction method and device, electronic equipment and computer storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101248432A (en) * | 2005-08-25 | 2008-08-20 | 慕迪灵公司 | Translation quality quantifying apparatus and method |
| CN102262621A (en) * | 2010-05-26 | 2011-11-30 | 钟长林 | Device and method for checking translated text |
| US20110313757A1 (en) * | 2010-05-13 | 2011-12-22 | Applied Linguistics Llc | Systems and methods for advanced grammar checking |
| CN103729345A (en) * | 2014-01-13 | 2014-04-16 | 三星电子（中国）研发中心 | Method and device for correcting wrong content in sent communication text |
| US20150302005A1 (en) * | 2012-07-13 | 2015-10-22 | Microsoft Technology Licensing, Llc | Phrase-based dictionary extraction and translation quality evaluation |
| CN106557478A (en) * | 2015-09-25 | 2017-04-05 | 四川省科技交流中心 | Distributed across languages searching systems and its search method based on bridge language |
-
2017
- 2017-12-11 CN CN201711310624.3A patent/CN107885728A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101248432A (en) * | 2005-08-25 | 2008-08-20 | 慕迪灵公司 | Translation quality quantifying apparatus and method |
| US20110313757A1 (en) * | 2010-05-13 | 2011-12-22 | Applied Linguistics Llc | Systems and methods for advanced grammar checking |
| CN102262621A (en) * | 2010-05-26 | 2011-11-30 | 钟长林 | Device and method for checking translated text |
| US20150302005A1 (en) * | 2012-07-13 | 2015-10-22 | Microsoft Technology Licensing, Llc | Phrase-based dictionary extraction and translation quality evaluation |
| CN103729345A (en) * | 2014-01-13 | 2014-04-16 | 三星电子（中国）研发中心 | Method and device for correcting wrong content in sent communication text |
| CN106557478A (en) * | 2015-09-25 | 2017-04-05 | 四川省科技交流中心 | Distributed across languages searching systems and its search method based on bridge language |
Non-Patent Citations (1)
| Title |
|---|
| 王华树: "《翻译技术教程》", 31 August 2017 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108984525A (en) * | 2018-07-06 | 2018-12-11 | 北京邮电大学 | A kind of Chinese grammer error-detecting method based on the term vector that text information is added |
| CN108984525B (en) * | 2018-07-06 | 2019-07-12 | 北京邮电大学 | A kind of Chinese grammer error-detecting method based on the term vector that text information is added |
| CN109522563A (en) * | 2018-10-15 | 2019-03-26 | 语联网（武汉）信息技术有限公司 | Judge automatically the method and device that statement translation finishes |
| CN109522563B (en) * | 2018-10-15 | 2023-05-23 | 语联网（武汉）信息技术有限公司 | Method and device for automatically judging statement translation completion |
| CN109359306A (en) * | 2018-10-16 | 2019-02-19 | 传神语联网网络科技股份有限公司 | Translation bearing calibration and system based on reiterant sentences detection |
| 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 |
| CN111191440A (en) * | 2019-12-13 | 2020-05-22 | 语联网（武汉）信息技术有限公司 | Method and system for measuring word error correction for translated text in translation |
| CN111191440B (en) * | 2019-12-13 | 2024-02-20 | 语联网（武汉）信息技术有限公司 | Method and system for correcting word measure and error for translation in translation |
| CN112036136A (en) * | 2020-09-01 | 2020-12-04 | 文思海辉智科科技有限公司 | Quality inspection data processing method and device, electronic equipment and readable storage medium |
| CN112215015A (en) * | 2020-09-02 | 2021-01-12 | 文思海辉智科科技有限公司 | Translation text revision method, translation text revision device, computer equipment and storage medium |
| CN113743101A (en) * | 2021-08-17 | 2021-12-03 | 北京百度网讯科技有限公司 | Text error correction method and device, electronic equipment and computer storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107885728A (en) | A kind of QA automatic testing methods and system based on interpreter's translation on line | |
| US7088949B2 (en) | Automated essay scoring | |
| Juergens et al. | Can clone detection support quality assessments of requirements specifications? | |
| US7127208B2 (en) | Automated annotation | |
| US10108904B2 (en) | Combining different type coercion components for deferred type evaluation | |
| CN107329967A (en) | Question answering system and method based on deep learning | |
| CN105868179A (en) | Intelligent asking-answering method and device | |
| CN107273883A (en) | Decision-tree model training method, determine data attribute method and device in OCR result | |
| US20210350521A1 (en) | Method for computer-implemented determination of blade-defects of a wind turbine | |
| EP4170605A1 (en) | Multi-level transferable region-based domain adaptive object detection apparatus and method | |
| CN110135225A (en) | Sample mask method and computer storage medium | |
| Ferrari et al. | Interview review: detecting latent ambiguities to improve the requirements elicitation process | |
| CN106844340A (en) | News in brief generation and display methods, apparatus and system based on artificial intelligence | |
| CN112036153A (en) | Work order error correction method and device, computer readable storage medium and computer equipment | |
| Seki et al. | Detecting bad smells in use case descriptions | |
| CN105701076A (en) | Thesis plagiarism detection method and system | |
| CN110610003A (en) | Method and system for assisting text annotation | |
| US20020103837A1 (en) | Method for handling requests for information in a natural language understanding system | |
| CN116611071A (en) | Function-level vulnerability detection method based on multiple modes | |
| CN112035619A (en) | Medical questionnaire screening method, device, equipment and medium based on artificial intelligence | |
| Kocerka et al. | Analysing quality of textual requirements using natural language processing: A literature review | |
| Gill et al. | Semi-automation for ambiguity resolution in Open Source Software requirements | |
| Vu et al. | Revising FUNSD dataset for key-value detection in document images | |
| CN116089262A (en) | Code security scanning system and method based on code dynamic analysis | |
| CN107577760B (en) | text classification method and device based on constraint specification |
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: 20180406 |
|
| RJ01 | Rejection of invention patent application after publication |