CN110837742A - Man-machine combined translation batch processing translation method containing artificial intelligence - Google Patents
Man-machine combined translation batch processing translation method containing artificial intelligence Download PDFInfo
- Publication number
- CN110837742A CN110837742A CN201911122404.7A CN201911122404A CN110837742A CN 110837742 A CN110837742 A CN 110837742A CN 201911122404 A CN201911122404 A CN 201911122404A CN 110837742 A CN110837742 A CN 110837742A
- Authority
- CN
- China
- Prior art keywords
- translation
- translated
- quality inspection
- artificial intelligence
- text
- 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
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Educational Administration (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- General Business, Economics & Management (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Machine Translation (AREA)
Abstract
The invention discloses a human-computer combined translation batch processing translation method containing artificial intelligence, which comprises the following steps: step 1, creating a translation project; step 2, uploading a file to be translated; step 3, the system analyzes and extracts the sentence break of the file and defines high-frequency words and terms; step 4, locking the repeated sentences of the original text; step 5, the system automatically fuzzily translates the matched original text according to the translation memory corpus; step 6, calling machine translation by the system according to the translation direction and the specialty to translate the rest original text; 7, performing quality inspection on the translated text of the fuzzy translation and the machine translation; step 8, checking and modifying the fuzzy translation and the machine translation on line by manpower; step 9, performing quality inspection on the result of the manual translation; and step 10, counting relevant parameters such as manual editing modification amplitude, word number and the like and generating a quality evaluation model report. The invention improves the translation efficiency, ensures the translation quality and reduces the translation cost.
Description
Technical Field
The invention relates to the technical field of file processing, language processing and the like, in particular to a human-computer combined translation batch processing translation method with artificial intelligence.
Background
The post-translation editing is used as necessary supplement of machine translation including artificial intelligent translation, and has important effects on improving the quality and efficiency of translated text and compressing the translation cost. The common post-translation editing modes are:
mode 1: the error detection and modification are carried out on the result obtained by the machine translation by manpower.
Mode 2: firstly, fuzzy matching translation is carried out through the translation memory corpus, then machine translation is carried out, and finally error detection and modification are carried out on the translation memory corpus and the machine translation manually.
The 2 ways of editing after translation reduce the translation workload to a certain extent. However, the machine-translated translation is completely subjected to error detection and modification by manpower, which consumes a large amount of work and cannot ensure the quality of the translation.
Machine translation techniques also have certain drawbacks, such as: the grammar is not smooth, and the translation is distorted. If the translation is checked and modified manually, much time is consumed, which is often longer than that of the manual translation used in the whole text, and the omission is easy to generate.
Disclosure of Invention
The invention aims to provide a man-machine combined translation batch processing translation method containing artificial intelligence, which realizes the same batch operation processing translation through the technologies of file parsing sentence breaking, original translation \ original standard writing, translation repeated sentence locking, multi-document multi-person simultaneous editing and the like so as to improve the translation efficiency; by combining translation memory corpora, a machine translation technology and manual translation, the translation efficiency of the translated text is greatly improved on the basis of ensuring the quality; the quality inspection technology is used for deeply analyzing the machine translation and the manual translation, the problems of the machine translation and the manual translation are detected, the translation quality is ensured while the translation workload is reduced, the translation cost is reduced, and the efficiency is improved, so that the problems in the background technology are solved.
In order to achieve the purpose, the invention provides the following technical scheme:
a human-computer combined translation batch processing translation method containing artificial intelligence comprises the following steps:
step 1, creating a translation project, setting translation direction, industry and other project information, and selecting translation memory corpus and machine translation;
step 2, uploading a file to be translated;
step 3, the system analyzes and extracts the sentence break of the file and defines high-frequency words and terms;
step 4, locking repeated sentences of the original text, wherein the repeated sentences after locking only need to translate the first sentence, and the rest sentences are automatically translated;
step 5, the system automatically fuzzily translates the matched original text according to the translation memory corpus;
step 6, calling machine translation by the system according to the translation direction and the specialty to translate the rest original text;
7, performing quality inspection on the translated text subjected to fuzzy translation and machine translation, displaying the error position and the error category of the translated text after quality inspection, and suggesting a translated text prompt;
step 8, checking and modifying the fuzzy translation and the machine translation on line by manpower, wherein the step can operate multi-person editing of multiple documents, namely combining multiple files in the same editor interface for editing, and can ensure the unification of terms and expressions of the same project;
step 9, quality inspection is carried out on the results of the manual translation, after quality inspection, the wrong position and the wrong type of the translated text are displayed, and translation prompt is suggested;
and step 10, counting relevant parameters such as manual editing modification amplitude, word number and the like and generating a quality evaluation model report.
Furthermore, the meaning of the sentence break analysis is that the uploaded file is firstly analyzed, and then sentence break processing conforming to language logic is carried out on the original text of the file according to rules such as language sentence dividing symbols, line feed in sections and the like.
Further, the extraction and definition of the high-frequency words and terms are as follows: and extracting high-frequency words and terms from the analyzed original text by a special technology, matching and extracting the words and terms of the original text according to the uploaded word bank in each professional field, and defining the terms.
Furthermore, the meaning of locking the repeated sentences is that the repeated sentences are locked across the files by matching the sentences of all the files of the project, the first sentence is only needed to be translated for the locked repeated sentences, and the rest sentences are automatically translated.
Furthermore, the meaning of the corpus matching is that the system compares and matches the language corpus and the original text according to the translation memory, and automatically translates the translated text with higher similarity with the original text.
Further, machine translation means that machine translation engines in different professional fields are called to translate to generate translated texts according to the specialties to which the translated files belong.
Further, the machine translation engine is implemented in the form of a call interface.
Furthermore, quality inspection comprises single-language quality inspection and double-language quality inspection, context quality early warning is carried out, a wrong part of the translated text is inspected through a certain technical means, the wrong position and the wrong type of the translated text are displayed after quality inspection, and translated text prompt is suggested.
Compared with the prior art, the invention has the beneficial effects that: the method realizes the same-class batch operation processing of translated text by the technologies of document analysis sentence break, original text translation \ original text standard writing, translation repeated sentence locking, multi-document multi-person simultaneous editing and the like so as to improve the translation efficiency; by combining translation memory corpora, a machine translation technology and manual translation, the translation speed of the translated text is greatly improved on the basis of ensuring the quality; machine translation and manual translation are deeply analyzed through a quality inspection technology, the problems existing in the machine translation and the manual translation are detected, the translation quality is ensured while the translation workload is reduced, the translation cost is reduced, and the efficiency is improved.
Drawings
FIG. 1 is a flowchart of a human-computer combined translation batch processing translation method including artificial intelligence according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
A human-computer combined translation batch processing translation method containing artificial intelligence is disclosed, the flow is shown as figure 1, and the method comprises the following steps:
step 1, creating a translation project, setting translation direction, industry and other project information, and selecting translation memory corpus and machine translation;
step 2, uploading a file to be translated;
step 3, the system analyzes and extracts the sentence break of the file and defines high-frequency words and terms;
sentence breaking analysis: the uploaded file is firstly analyzed (the original format of the file can be reserved), and then sentence breaking processing is carried out on the original file text according to rules such as language sentence dividing symbols, line feed in sections and the like.
Extracting and defining high-frequency words and terms: and extracting high-frequency words and terms from the analyzed original text by a special technology, matching and extracting the words and terms of the original text according to the uploaded word bank in each professional field, and defining the terms. High-frequency words: the vocabulary with the frequency of appearance more than or equal to 2 times in the original text; the terms: the vocabularies matched with the uploaded professional lexicon and the special words defined by the professional manual judgment.
And step 4, repeating sentence locking: by matching sentences of all documents of the project, the repeated sentences are locked across the documents, and if the repeated sentences except the first sentence are not required to be locked and other repeated sentences are all locked, the locked repeated sentences only need to be translated into the first sentence, and other sentences are automatically translated.
Step 5, the system automatically fuzzily translates the matched original text according to the translation memory corpus;
and (3) corpus matching: the system compares and matches the language materials and the original text according to the translation memory language materials, and automatically translates the translated text with higher similarity with the original text in a matching way.
And 6, calling machine translation by the system according to the translation direction and the specialty to translate the rest original text.
And (3) machine translation: and calling machine translation engines in different professional fields to translate according to the specialties to which the translation files belong to so as to generate translated texts.
7, performing quality inspection on the translated text subjected to fuzzy translation and machine translation, displaying the error position and the error category of the translated text after quality inspection, and suggesting a translated text prompt;
step 8, checking and modifying the fuzzy translation and the machine translation on line by manpower, wherein the step can operate multi-person editing of multiple documents, namely combining multiple files in the same editor interface for editing, and can ensure the unification of terms and expressions of the same project;
and 9, performing quality inspection on the result of the manual translation, displaying the error position and the error category of the translated text after the quality inspection, and suggesting a translated text translation prompt. Quality inspection: the method comprises the steps of monolingual quality inspection, bilingual quality inspection and context quality early warning. And checking the wrong part of the translated text by a certain technical means, displaying the wrong position and the wrong type of the translated text after quality inspection, and suggesting a translated text prompt.
(1) And (3) single language quality inspection: other errors such as grammar errors, spelling errors, punctuation errors, Chinese wrongly written or mispronounced characters and the like are realized by calling an interface; the 'unused term' checks whether the translation is applied to the target term library through the translation sentence and the target term library; the repeated words are obtained by checking whether the translated text has repeated characters;
(2) bilingual quality inspection: through the matching of the original text and the translated text and according to a certain rule, errors such as missed translated sentences, numerical errors, link errors, label mismatching, identical translated text and the like are detected.
(3) Context quality early warning: and judging the early warning of the quality of the translation according to the context, and carrying out manual intervention.
Multi-document editing: a plurality of file sentences are combined in the same editor, and editing and similar batch operation are carried out on the file sentences.
And step 10, counting relevant parameters such as manual editing modification amplitude, word number and the like and generating a quality evaluation model report.
(1) And manual editing and modifying amplitude: and (4) correcting and editing the result after the machine translation by a human, and accounting for the part with the difference generated by comparing the result after the machine translation with the result after the machine translation.
(2) Quality evaluation model: and establishing a quality evaluation model for the work in the post-translation edition by using a related technology to show whether the work quality in the post-translation edition meets the related standard of a country or an industry and a client.
The nouns of the related art terms of the present invention are explained as follows:
compared with the modern technology, the invention has the following advantages:
1. the method and the device have the advantages that the sentences of all documents of the project are matched, the repeated sentences are locked across the documents, the first sentence is only needed to be translated for the locked repeated sentences, and the rest sentences are automatically translated, so that the translation amount is reduced.
2. The invention adopts machine translation, and calls machine translation engines in different fields through different translation specialties, thereby improving the quality of translated texts.
3. According to the invention, through a language quality inspection technology, the unqualified translated text translated by a machine is edited and classified after being manually translated, and the translation quality inspection technology is applied to a manual translation scene. The method reduces human translation errors, fully exerts the efficiency brought by a machine translation technology, fully exerts the quality of human translation, and meets the requirement of rapid development of a language service market.
4. According to the invention, through a mode of simultaneously editing multiple files on line by multiple persons, resource synchronous sharing and similar batch operation of translated texts by manual translation are facilitated, the uniformity of the translated texts is realized, and the translation efficiency and the translation quality are greatly improved.
The invention provides a quality inspection technology, which is used for firstly carrying out quality inspection on a translated text after machine translation and inspecting partial translation problems of the machine translation to a certain extent. And the quality inspection technology is applied to the manual translation scene, so that the manual translation errors are reduced, and the translation quality is improved. The efficiency improvement effect brought by the machine translation technology is fully exerted, the quality assurance effect of manual translation is fully exerted, and the requirement for rapid development of the language service market is met.
The invention carries out modeling according with national or industrial standards on the result of manually correcting the machine translation and the result of intelligent translation so as to evaluate the working quality of manual and intelligent translation. So as to eliminate the subjective influence of human factors on the evaluation of the manual work result and the intelligent translation result and achieve fairness and justice. And the working quality is rapidly and quantitatively evaluated, the defects of manual work and intelligent translation are improved, and the quality and the efficiency of the manual work are improved.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be able to cover the technical solutions and the inventive concepts of the present invention within the technical scope of the present invention.
Claims (7)
1. A human-computer combined translation batch processing translation method containing artificial intelligence is characterized by comprising the following steps:
step 1, creating a translation project, setting translation direction, industry and other project information, and selecting translation memory corpus and machine translation;
step 2, uploading a file to be translated;
step 3, the system analyzes and extracts the sentence break of the file and defines high-frequency words and terms;
step 4, locking repeated sentences of the original text, wherein the repeated sentences after locking only need to translate the first sentence, and the rest sentences are automatically translated;
step 5, the system automatically fuzzily translates the matched original text according to the translation memory corpus;
step 6, calling machine translation by the system according to the translation direction and the specialty to translate the rest original text;
7, performing quality inspection on the translated text subjected to fuzzy translation and machine translation, displaying the error position and the error category of the translated text after quality inspection, and suggesting a translated text prompt;
step 8, checking and modifying the fuzzy translation and the machine translation on line by manpower, wherein the step can operate multi-person editing of multiple documents, namely combining multiple files in the same editor interface for editing, and can ensure the unification of terms and expressions of the same project;
step 9, quality inspection is carried out on the results of the manual translation, after quality inspection, the wrong position and the wrong type of the translated text are displayed, and translation prompt is suggested;
and step 10, counting relevant parameters such as manual editing modification amplitude, word number and the like and generating a quality evaluation model report.
2. The human-computer combined translation batch processing translation method containing artificial intelligence of claim 1, wherein the meaning of sentence break analysis is that the uploaded file is firstly analyzed, and then sentence break processing conforming to language logic is carried out on the original file according to rules of language clause signs, segment line feed and the like.
3. The batch processing and translation method for human-computer combined translation containing artificial intelligence as claimed in claim 1, wherein the extraction and definition of the high frequency words and terms: and extracting high-frequency words and terms from the analyzed original text by a special technology, matching and extracting the words and terms of the original text according to the uploaded word bank in each professional field, and defining the terms.
4. The batch processing and translating method for human-computer combined translation with artificial intelligence as claimed in claim 1, wherein said corpus matching means that the system performs matching by comparing the translation memory corpus with the original text to match the automatic translation of the translation with higher similarity to the original text.
5. The human-computer combined translation batch processing translation method containing artificial intelligence of claim 1, wherein the meaning of machine translation is that according to the profession to which the translation document belongs, machine translation engines in different professions are called to translate to generate a translation.
6. The human-computer combined translation batch processing translation method containing artificial intelligence of claim 1, wherein a corresponding translation engine interface meeting the requirement is called according to the translation requirement.
7. The human-computer combined translation batch processing translation method comprising artificial intelligence as claimed in claim 1, wherein the quality inspection comprises monolingual quality inspection, bilingual quality inspection, context quality early warning and the like, the wrong part of the translated text is inspected by a certain technical means, the wrong position and the wrong type of the translated text are displayed after the quality inspection, and the translated text prompt is suggested.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911122404.7A CN110837742A (en) | 2019-11-15 | 2019-11-15 | Man-machine combined translation batch processing translation method containing artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911122404.7A CN110837742A (en) | 2019-11-15 | 2019-11-15 | Man-machine combined translation batch processing translation method containing artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110837742A true CN110837742A (en) | 2020-02-25 |
Family
ID=69576549
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911122404.7A Pending CN110837742A (en) | 2019-11-15 | 2019-11-15 | Man-machine combined translation batch processing translation method containing artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110837742A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111429231A (en) * | 2020-04-10 | 2020-07-17 | 广州市汇泉翻译服务有限公司 | Order system and method for translation-related language service |
| CN111507869A (en) * | 2020-03-10 | 2020-08-07 | 文思海辉智科科技有限公司 | Translation quality inspection extraction method and device, computer equipment and storage medium |
| CN111626066A (en) * | 2020-05-27 | 2020-09-04 | 辛钧意 | Paragraph translation system and method based on big data |
| 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 |
| CN112417898A (en) * | 2020-11-24 | 2021-02-26 | 掌阅科技股份有限公司 | Text translation method based on keyword prompt, computing device and storage medium |
| CN112487828A (en) * | 2020-11-27 | 2021-03-12 | 江苏省舜禹信息技术有限公司 | Error correction improved translation big data integration method |
| CN113792558A (en) * | 2021-11-16 | 2021-12-14 | 北京百度网讯科技有限公司 | Self-learning translation method and device based on machine translation and post-translation editing |
| CN113807106A (en) * | 2021-08-31 | 2021-12-17 | 北京百度网讯科技有限公司 | Translation model training method and device, electronic equipment and storage medium |
| CN115587599A (en) * | 2022-09-16 | 2023-01-10 | 粤港澳大湾区数字经济研究院(福田) | Quality detection method and device for machine translation corpus |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106777268A (en) * | 2016-12-28 | 2017-05-31 | 语联网（武汉）信息技术有限公司 | A kind of method of translation document storage and retrieval |
| CN107885737A (en) * | 2017-12-27 | 2018-04-06 | 传神语联网网络科技股份有限公司 | A kind of human-computer interaction interpretation method and system |
| CN107885728A (en) * | 2017-12-11 | 2018-04-06 | 中译语通科技股份有限公司 | A kind of QA automatic testing methods and system based on interpreter's translation on line |
| CN108519979A (en) * | 2018-02-28 | 2018-09-11 | 成都优译信息技术股份有限公司 | The method and system that translation memory library and MT are combined in a kind of CAT systems |
-
2019
- 2019-11-15 CN CN201911122404.7A patent/CN110837742A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106777268A (en) * | 2016-12-28 | 2017-05-31 | 语联网（武汉）信息技术有限公司 | A kind of method of translation document storage and retrieval |
| CN107885728A (en) * | 2017-12-11 | 2018-04-06 | 中译语通科技股份有限公司 | A kind of QA automatic testing methods and system based on interpreter's translation on line |
| CN107885737A (en) * | 2017-12-27 | 2018-04-06 | 传神语联网网络科技股份有限公司 | A kind of human-computer interaction interpretation method and system |
| CN108519979A (en) * | 2018-02-28 | 2018-09-11 | 成都优译信息技术股份有限公司 | The method and system that translation memory library and MT are combined in a kind of CAT systems |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111507869A (en) * | 2020-03-10 | 2020-08-07 | 文思海辉智科科技有限公司 | Translation quality inspection extraction method and device, computer equipment and storage medium |
| CN111429231A (en) * | 2020-04-10 | 2020-07-17 | 广州市汇泉翻译服务有限公司 | Order system and method for translation-related language service |
| CN111626066A (en) * | 2020-05-27 | 2020-09-04 | 辛钧意 | Paragraph translation system and method based on big data |
| 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 |
| CN112417898A (en) * | 2020-11-24 | 2021-02-26 | 掌阅科技股份有限公司 | Text translation method based on keyword prompt, computing device and storage medium |
| CN112487828A (en) * | 2020-11-27 | 2021-03-12 | 江苏省舜禹信息技术有限公司 | Error correction improved translation big data integration method |
| CN113807106A (en) * | 2021-08-31 | 2021-12-17 | 北京百度网讯科技有限公司 | Translation model training method and device, electronic equipment and storage medium |
| CN113807106B (en) * | 2021-08-31 | 2023-03-07 | 北京百度网讯科技有限公司 | Translation model training method and device, electronic equipment and storage medium |
| CN113792558A (en) * | 2021-11-16 | 2021-12-14 | 北京百度网讯科技有限公司 | Self-learning translation method and device based on machine translation and post-translation editing |
| CN115587599A (en) * | 2022-09-16 | 2023-01-10 | 粤港澳大湾区数字经济研究院(福田) | Quality detection method and device for machine translation corpus |
| CN115587599B (en) * | 2022-09-16 | 2023-07-14 | 粤港澳大湾区数字经济研究院(福田) | Quality detection method and device for machine translation corpus |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110837742A (en) | Man-machine combined translation batch processing translation method containing artificial intelligence | |
| CN109255113B (en) | Intelligent proofreading system | |
| CN107463553B (en) | Text semantic extraction, representation and modeling method and system for elementary mathematic problems | |
| CN110532573B (en) | Translation method and system | |
| CN105320960B (en) | Voting-based cross-language subjective and objective emotion classification method | |
| CN107885737B (en) | Man-machine interactive translation method and system | |
| RU2251737C2 (en) | Method for automatic recognition of language of recognized text in case of multilingual recognition | |
| Cho et al. | Segmentation and punctuation prediction in speech language translation using a monolingual translation system | |
| CN106598959B (en) | Method and system for determining mutual translation relationship of bilingual sentence pairs | |
| CN110770735A (en) | Transcoding of documents with embedded mathematical expressions | |
| CN108363691A (en) | A kind of field term identifying system and method for 95598 work order of electric power | |
| CN111143531A (en) | Question-answer pair construction method, system, device and computer readable storage medium | |
| CN114722842A (en) | Computer artificial intelligent foreign language translation method and translation system thereof | |
| CN111832281A (en) | Composition scoring method and device, computer equipment and computer readable storage medium | |
| CN111178061A (en) | Multi-lingual word segmentation method based on code conversion | |
| CN113158695A (en) | Semantic auditing method and system for multi-language mixed text | |
| CN110807338B (en) | English-Chinese machine translation term consistency self-correcting system and method | |
| CN109815503B (en) | Man-machine interaction translation method | |
| Hou et al. | Classification of regional and genre varieties of Chinese: A correspondence analysis approach based on comparable balanced corpora | |
| CN111178098A (en) | Text translation method, device and equipment and computer readable storage medium | |
| CN103164397B (en) | The Chinese breathes out the method that e-dictionary and its automatic translation Chinese breathe out language | |
| CN113037934A (en) | Hot word analysis system based on call recording of call center | |
| CN111126201B (en) | Character recognition method and device in script | |
| US20230069113A1 (en) | Text Summarization Method and Text Summarization System | |
| CN115983251A (en) | Text topic extraction system and method based on sentence analysis |
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 |