WO2011049313A2 - 표현 및 설명 추출을 위한 문서 처리 장치 및 방법 - Google Patents
표현 및 설명 추출을 위한 문서 처리 장치 및 방법 Download PDFInfo
- Publication number
- WO2011049313A2 WO2011049313A2 PCT/KR2010/006943 KR2010006943W WO2011049313A2 WO 2011049313 A2 WO2011049313 A2 WO 2011049313A2 KR 2010006943 W KR2010006943 W KR 2010006943W WO 2011049313 A2 WO2011049313 A2 WO 2011049313A2
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- expression
- description
- document
- sentence
- script
- 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.)
- Ceased
Links
Images
Classifications
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B19/00—Teaching not covered by other main groups of this subclass
- G09B19/06—Foreign languages
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/951—Indexing; Web crawling techniques
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/258—Heading extraction; Automatic titling; Numbering
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
Definitions
- the present invention relates to a document processing apparatus and method, and more particularly, to a document processing apparatus and method for collecting a document on the web and extracting a representation and description from the collected document.
- the problem to be solved by the present invention is to provide a document processing apparatus and method that can automatically build a learning material consisting of a pair of learning expressions and a description to explain the same from the Web.
- the document processing apparatus for solving the technical problem, a document collection unit for collecting a document from the web and separating the document into a script portion and a description portion to generate a script document and description document, and the And an expression extracting unit extracting an expression description sentence based on the description document, and extracting the expression described in the script document.
- the apparatus may further include a sentence extractor configured to extract a plurality of script sentences by separating sentences from the script document, and extract a plurality of description sentences by separating sentences from the description document.
- a sentence extractor configured to extract a plurality of script sentences by separating sentences from the script document, and extract a plurality of description sentences by separating sentences from the description document.
- the sentence extractor may classify which script sentence is a description of each of the plurality of script sentences.
- the sentence extractor may perform the classification using a conditional random field classifier.
- the expression extracting unit may extract the expression description sentence from the plurality of description sentences using a labeled sequential pattern technique.
- the expression extracting unit may extract the expression described by the expression description sentence in the script sentence by measuring the similarity between the expression description sentence and the expression in the script sentence.
- the similarity may be measured using a cosine similarity technique or an edit distance technique.
- the document collection unit may generate the script document and the description document based on an identifier or a sentence indicating a start or end of the script part and the description part.
- the apparatus may further include a database configured to store the extracted expression and expression description sentences describing the extracted expression.
- the apparatus may further include a data providing unit providing the user with an expression description sentence describing the extracted expression and the extracted expression in response to a request from the user.
- the document may be written in English.
- a language teaching system includes any of the above devices.
- a document processing method comprising: collecting a document from a web and dividing the document into a script portion and a description portion to generate a script document and a description document, and generating an expression description sentence based on the description document. And extracting the expression in which the expression description sentence is described in the script document.
- the method may further include extracting a plurality of script sentences by separating sentences from the script document, and extracting a plurality of description sentences by separating sentences from the description document.
- the sentence extracting step may include classifying which script sentence of each of the plurality of script sentences is a description of the script sentence.
- the classifying step may include using a conditional random field classifier.
- the expression extracting step may include extracting the expression description sentence from the plurality of description sentences using a labeled sequential pattern technique.
- the expression extracting step may include extracting an expression in which the expression description sentence is described in the script sentence by measuring the similarity between the expression description sentence and the expression in the script sentence.
- the similarity may be measured using a cosine similarity technique or an edit distance technique.
- the document generation step may generate the script document and the description document based on an identifier or a sentence indicating the start or end of the script part and the description part.
- the method may further include storing the extracted expression and an expression description sentence describing the extracted expression.
- the method may further include providing the extracted expression and an expression description sentence describing the extracted expression to the user according to a request from the user.
- the language teaching method according to another aspect of the present invention includes any of the above methods.
- a computer readable medium records a program for causing a computer to execute any of the above methods.
- FIG. 1 is a block diagram illustrating a document processing apparatus according to an embodiment of the present invention.
- FIG. 2 is a diagram illustrating documents collected by a document processing apparatus according to an embodiment of the present invention.
- FIG. 3 is a flowchart illustrating a document processing method according to an embodiment of the present invention.
- FIG. 1 is a block diagram illustrating a document processing apparatus according to an embodiment of the present invention
- Figure 2 is a diagram illustrating a document collected by the document processing apparatus according to an embodiment of the present invention.
- a document processing apparatus 100 is connected to a web server 200 and a user terminal 300 through a communication network 400.
- the document processing apparatus 100 automatically extracts and stores a learning expression and a description thereof from a document collected through a web page provided by the web server 200.
- the document processing apparatus 100 receives a query from the user terminal 300 and provides the user terminal 300 with learning material including a learning expression corresponding to the query and a description thereof.
- the web server 200 provides a web page in response to a request from the user terminal 300 and the document processing apparatus 100 through the communication network 400.
- the web server 200 may provide a web page through a language education site, and the document processing apparatus 100 may extract a predetermined document from various documents included in the web page.
- the web site "www.eslpod.com” provides documentation that includes English scripts and descriptions.
- the document processing apparatus 100 performs a task with a predetermined document extracted from this site.
- the document processing apparatus 100 can also extract the document required for a job from another site.
- the document DC provided by the site “www.eslpod.com” includes a script part SP and a description part DP.
- various stories are developed in the script portion SP, and in the description portion DP, the meaning or usage of the expression in the script portion SP is described.
- the document (DC) is described as being written in English, but is not limited thereto and may be other languages such as Korean, Japanese, German, and Chinese.
- Expression is a unit that conveys at least one meaning and consists of morphemes, words or idioms, and combinations thereof. For the sake of convenience, the expression will also be described in English, but the expression is not limited thereto.
- the user terminal 300 is a communication terminal device used by a user to receive a web service.
- the user terminal 300 accesses a web server 200, a document processing apparatus 100, and the like through the communication network 400 to exchange information.
- the user terminal 300 may be a desktop computer as well as a laptop computer, a workstation, a palmtop computer, an ultra mobile personal computer, a tablet PC, a personal digital assistant (PDA), a web pad, a mobile phone. It may be made of a terminal having a computing power by including a memory means and a microprocessor.
- the communication network 400 may include a telephone network as well as a data communication network including a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), the Internet, and the like. It can be used, and it does not matter wired and wireless, and it does not matter which communication method is used.
- LAN local area network
- MAN metropolitan area network
- WAN wide area network
- the Internet and the like. It can be used, and it does not matter wired and wireless, and it does not matter which communication method is used.
- the document processing apparatus 100 includes a document collecting unit 110, a sentence extracting unit 130, an expression extracting unit 150, a database 170, and a data providing unit 190.
- the document collector 110 collects a document from a web site provided by the web server 200.
- the document can be extracted from a predetermined web site, such as "www.eslpod.com", and includes a script and description.
- a script refers to a short story on a particular topic, and does not cover statements or dialogs.
- the document collection unit 110 generates a script document and a description document by extracting the script part and the description part from the collected documents based on an identifier or a sentence indicating the start or end of the script part and the description part.
- the identifier ⁇ start of story> indicates the beginning of the script portion SP
- the identifier ⁇ end of story> indicates the end of the script portion SP and the description portion DP. It can indicate the beginning.
- the identifier may exist in various forms such as a specific symbol such as '*' or ' ⁇ ' or a word such as 'start' or 'end'.
- the sentence extractor 130 separates each script sentence from the script document and separates each description sentence from the description document based on an identifier such as a symbol indicating an end of a sentence such as a period, question mark, or exclamation mark. Thereafter, the sentence extractor 130 classifies which script sentence is a description of each description sentence.
- a conditional random field (CRF) classifier may be used to classify the description sentence, but is not limited thereto.
- Conditional random field classifier is a kind of discriminative probabilistic model classifier used for labeling or parsing sequential data, such as natural language text.
- the classification result is represented as a binary classification for each i-th script sentence, whether each description sentence is a description of the i-th script sentence.
- the number of script sentences included in one script document is M
- each description sentence of the description document is input to the classifier for the i-th script sentence, and all description sentences of the description document are inputted.
- the binary classification result is output. If the classification process is performed on all script sentences (1 ⁇ i ⁇ M), the description sentences corresponding to each script sentence can be extracted, and thus, the classification of each sentence of the description document is a description of the script document. can do.
- description sentences corresponding to a script sentence are called sentence descriptions of the script sentence.
- there may not be a description sentence corresponding to the script sentence and there may be a description sentence not corresponding to the script sentence among the description sentences.
- the expression extracting unit 150 extracts the expression description sentence from the sentence description and finds out and extracts what expression the extracted expression description sentence describes in the script sentence.
- the expression extracting unit 150 performs binary classification on all sentences of the extracted whole sentence description as to whether each sentence has an explanatory form of the English expression.
- a labeled sequential pattern (LSP) technique may be used, but is not limited thereto.
- the LSP technique is a method of patterning a sentence when a sentence is given. For example, the word "Where can I find a job?" Is replaced with "Where can PRN VB DT NN?” How to substitute a larger range of classes. Where PRN is a pronoun, VB is a verb, DT is an article, and NN is a noun.
- Patterns that can represent descriptive forms of English expressions can be trained from documents that include script portions and description portions. For example, the expression “... means to ! or "... is a ## which are often used to describe English expressions, is trained in patterns. According to this pattern, expression description sentences representing English expressions may be extracted by performing binary classification on each sentence of the entire sentence description.
- the expression extracting unit 150 extracts an English expression in the corresponding script sentence that the extracted expression description sentence describes.
- the expression extracting unit 150 extracts the English expression described by the expression description sentence based on the similarity between the expression in the script sentence and the expression description sentence. Similarity is used to compare documents, for example in text mining, and a cosine similarity technique that can measure similarity between texts or an edit distance that can measure the distance between strings. ) Technique may be used, but is not limited thereto.
- the expression extracting unit 150 extracts the corresponding English expression for the entire expression description sentence through this method, and stores the extracted English expression and the expression description sentence describing the same in the database 170. At this time, the expression extracting unit 150 uses a pair of English expressions and expression description sentences describing the same (hereinafter referred to as 'expression-description sentence pairs' describing English expressions and the 'expression-description pairs') to the database 170. Can be stored.
- the database 170 stores the expression-description pair provided by the expression extraction unit 150 and provides the expression-description pair at the request of the data provider 190.
- the data provider 190 performs an indexing operation on the expression-description pair so that the database 170 can be easily searched.
- the database 170 performs a pre-processing process such as extracting a best expression for the query through analysis, and then expresses the expression-description pair including the corresponding expression. Search for and provide the retrieved expression-description pair to the user terminal 300.
- the learning material consisting of a pair of English expressions and a description thereof may be collected and automatically constructed from the web. These materials can be used for the automatic construction of word and phrase dictionaries and can be used as educational materials throughout software for foreign language education.
- the document processing apparatus 100 searches for and presents an appropriate pair of English expressions and description sentences when an explanation is required for an English expression that an actual user does not understand or is not familiar with through an expression and description database. can do.
- English expressions and explanations using web documents, it is possible to provide detailed explanations, including expression usage in actual scripts, compared to English dictionary search results of Korean descriptions containing only dictionary meanings. Since it is in English, the original meaning can be provided without being compromised by the translation.
- the document processing apparatus 100 may be used to collect expression-description pairs for language education, and thus may be included in various systems (not shown) for language education. Examples of such systems include, but are not limited to, online dictionary systems or interactive educational systems.
- the document processing apparatus 100 may be implemented not to include at least one of the database 170 and the data providing unit 190.
- the database 170 and / or the data management system may be implemented.
- Study 190 may be included in a foreign language education system, such as an English conversation system.
- the document processing apparatus 100 may be implemented in an independent server form, but may be implemented in an integrated form with the user terminal 300. That is, all of the functions of the document processing apparatus 100 may be implemented in the user terminal 300 to collect a web document from the user terminal 300 and extract a representation-description pair therefrom. You can retrieve the pair and provide it to the user. Of course, some of the functions of the document processing apparatus 100 may be implemented in the user terminal 300.
- FIG. 3 is a flowchart illustrating a document processing method according to an embodiment of the present invention.
- the document processing apparatus 100 collects a document including a script and a description thereof from a web site provided by the web server 200 (S510). Thereafter, the document processing apparatus 100 generates a script document and a description document by extracting the script part and the description part from the collected documents based on identifiers or sentences indicating the start and end of the script part and the description part (S520). .
- the document processing apparatus 100 separates each script sentence from the script document and separates each description sentence from the description document based on an identifier such as a symbol indicating the end of a sentence such as a period, a question mark, an exclamation mark, or the like (S530). Thereafter, the document processing apparatus 100 classifies which script sentences each description sentence describes using a CRF classifier or the like (S540).
- the document processing apparatus 100 performs a binary classification on whether each sentence has an explanatory form of the English expression for all sentences of the entire sentence description extracted by using the LSP technique, and then describes the explanatory form of the English expression.
- the document processing apparatus 100 extracts an English expression in which the extracted expression description sentences are explained in the corresponding script sentence.
- the document processing apparatus 100 may extract the English expression described by the expression description sentence by measuring the similarity between the expression description sentence extracted using the cosine similarity technique or the editing distance technique and the expression in the script sentence.
- the document processing apparatus 100 stores the extracted English expression and the expression description sentence for explaining the same (S570).
- the document processing apparatus 100 may store the English expression and the expression description sentence describing the pair as a document.
- the document processing apparatus 100 receives a query from the user terminal 300, performs a preprocessing process such as analyzing a query and extracting an expression most suitable for the query, and searching for a document including the expression in the database 170.
- the searched result is transmitted to the user terminal 300.
- the document processing method may be used to collect expressions for foreign language education and pairs of description sentences thereof, and thus may be included in various methods for foreign language education. Examples of such a method may include, but are not limited to, an online dictionary providing method or an interactive teaching method.
- Embodiments of the invention include a computer readable medium containing program instructions for performing various computer-implemented operations.
- This medium records a program for executing the document processing method described so far.
- the media may include, alone or in combination with the program instructions, data files, data structures, and the like. Examples of such media include magnetic media such as hard disks, floppy disks and magnetic tape, optical recording media such as CDs and DVDs, floppy disks and program commands such as magnetic-optical media, ROM, RAM and flash memory. Hardware devices configured to store and perform such operations.
- the medium may be a transmission medium such as an optical or metal wire, a waveguide, or the like including a carrier wave for transmitting a signal specifying a program command, a data structure, and the like.
- Examples of program instructions include not only machine code generated by a compiler, but also high-level language code that can be executed by a computer using an interpreter or the like.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- Educational Technology (AREA)
- Educational Administration (AREA)
- Entrepreneurship & Innovation (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Marketing (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Document Processing Apparatus (AREA)
- Machine Translation (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
Description
Claims (25)
- 웹으로부터 문서를 수집하고 상기 문서를 스크립트 부분과 설명 부분으로 분리하여 스크립트 문서 및 설명 문서를 생성하는 문서 수집부, 그리고상기 설명 문서에 기초하여 표현 설명 문장을 추출하고 상기 표현 설명 문장이 상기 스크립트 문서 내에서 설명하고 있는 표현을 추출하는 표현 추출부를 포함하는 문서 처리 장치.
- 제1항에서,상기 스크립트 문서에서 문장을 분리하여 복수의 스크립트 문장을 추출하고 상기 설명 문서에서 문장을 분리하여 복수의 설명 문장을 추출하는 문장 추출부를 더 포함하는 문서 처리 장치.
- 제2항에서,상기 문장 추출부는 각 설명 문장이 상기 복수의 스크립트 문장 중 어느 스크립트 문장에 대한 설명인지 분류하는 문서 처리 장치.
- 제3항에서,상기 문장 추출부는 조건부 랜덤 필드(conditional random field) 분류기를 사용하여 상기 분류를 수행하는 문서 처리 장치.
- 제2항에서,상기 표현 추출부는 레이블드 순차 패턴(labeled sequential pattern) 기법을 이용하여 상기 복수의 설명 문장으로부터 상기 표현 설명 문장을 추출하는 문서 처리 장치.
- 제2항에서,상기 표현 추출부는 상기 표현 설명 문장과 상기 스크립트 문장 내의 표현의 유사도를 측정하여 상기 표현 설명 문장이 상기 스크립트 문장 내에서 설명하고 있는 표현을 추출하는 문서 처리 장치.
- 제6항에서,상기 유사도는 코사인 유사도(cosine similarity) 기법이나 편집 거리(edit distance) 기법을 사용하여 측정되는 문서 처리 장치.
- 제1항에서,상기 문서 수집부는 상기 스크립트 부분 및 상기 설명 부분의 시작 또는 끝을 나타내는 식별자 또는 문장에 기반하여 상기 스크립트 문서 및 상기 설명 문서를 생성하는 문서 처리 장치.
- 제1항에서,상기 추출된 표현과 상기 추출된 표현을 설명하는 표현 설명 문장을 저장하는 데이터베이스를 더 포함하는 문서 처리 장치.
- 제1항에서,사용자로부터의 요청에 따라 상기 추출된 표현과 상기 추출된 표현을 설명하는 표현 설명 문장을 상기 사용자에게 제공하는 자료 제공부를 더 포함하는 문서 처리 장치.
- 제1항에서,상기 문서는 영어로 작성되어 있는 문서 처리 장치.
- 제1항 내지 제11항 중 어느 한 항의 문서 처리 장치를 포함하는 어학 교육 시스템.
- 웹으로부터 문서를 수집하고 상기 문서를 스크립트 부분과 설명 부분으로 분리하여 스크립트 문서 및 설명 문서를 생성하는 단계, 그리고상기 설명 문서에 기초하여 표현 설명 문장을 추출하고 상기 표현 설명 문장이 상기 스크립트 문서 내에서 설명하고 있는 표현을 추출하는 단계를 포함하는 문서 처리 방법.
- 제13항에서,상기 스크립트 문서에서 문장을 분리하여 복수의 스크립트 문장을 추출하고 상기 설명 문서에서 문장을 분리하여 복수의 설명 문장을 추출하는 단계를 더 포함하는 문서 처리 방법.
- 제14항에서,상기 문장 추출 단계는 각 설명 문장이 상기 복수의 스크립트 문장 중 어느 스크립트 문장에 대한 설명인지 분류하는 단계를 포함하는 문서 처리 방법.
- 제15항에서,상기 분류 단계는 조건부 랜덤 필드(conditional random field) 분류기를 사용하는 단계를 포함하는 문서 처리 방법.
- 제14항에서,상기 표현 추출 단계는 레이블드 순차 패턴(labeled sequential pattern) 기법을 이용하여 상기 복수의 설명 문장으로부터 상기 표현 설명 문장을 추출하는 단계를 포함하는 문서 처리 방법.
- 제14항에서,상기 표현 추출 단계는 상기 표현 설명 문장과 상기 스크립트 문장 내의 표현의 유사도를 측정하여 상기 표현 설명 문장이 상기 스크립트 문장 내에서 설명하고 있는 표현을 추출하는 단계를 포함하는 문서 처리 방법.
- 제18항에서,상기 유사도는 코사인 유사도(cosine similarity) 기법이나 편집 거리(edit distance) 기법을 사용하여 측정되는 문서 처리 방법.
- 제13항에서,상기 문서 생성 단계는 상기 스크립트 부분 및 상기 설명 부분의 시작 또는 끝을 나타내는 식별자 또는 문장에 기반하여 상기 스크립트 문서 및 상기 설명 문서를 생성하는 문서 처리 방법.
- 제13항에서,상기 추출된 표현과 상기 추출된 표현을 설명하는 표현 설명 문장을 저장하는 단계를 더 포함하는 문서 처리 방법.
- 제13항에서,사용자로부터의 요청에 따라 상기 추출된 표현과 상기 추출된 표현을 설명하는 표현 설명 문장을 상기 사용자에게 제공하는 단계를 더 포함하는 문서 처리 방법.
- 제13항에서,상기 문서는 영어로 작성되어 있는 문서 처리 방법.
- 제13항 내지 제23항 중 어느 한 항의 문서 처리 방법을 포함하는 어학 교육 방법.
- 컴퓨터에 제13항 내지 제23항 중 어느 한 항의 방법을 실행시키기 위한 프로그램을 기록한 컴퓨터로 읽을 수 있는 매체.
Priority Applications (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| US13/498,322 US8666987B2 (en) | 2009-10-23 | 2010-10-11 | Apparatus and method for processing documents to extract expressions and descriptions |
| CN201080046722.0A CN102576367B (zh) | 2009-10-23 | 2010-10-11 | 用于提取短语及说明的文档处理装置及方法 |
| JP2012530792A JP5690829B2 (ja) | 2009-10-23 | 2010-10-11 | 表現および説明抽出のための文書処理装置および方法 |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| KR1020090100962A KR101072100B1 (ko) | 2009-10-23 | 2009-10-23 | 표현 및 설명 추출을 위한 문서 처리 장치 및 방법 |
| KR10-2009-0100962 | 2009-10-23 |
Publications (3)
| Publication Number | Publication Date |
|---|---|
| WO2011049313A2 true WO2011049313A2 (ko) | 2011-04-28 |
| WO2011049313A9 WO2011049313A9 (ko) | 2011-06-30 |
| WO2011049313A3 WO2011049313A3 (ko) | 2011-09-01 |
Family
ID=43900780
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/KR2010/006943 Ceased WO2011049313A2 (ko) | 2009-10-23 | 2010-10-11 | 표현 및 설명 추출을 위한 문서 처리 장치 및 방법 |
Country Status (5)
| Country | Link |
|---|---|
| US (1) | US8666987B2 (ko) |
| JP (1) | JP5690829B2 (ko) |
| KR (1) | KR101072100B1 (ko) |
| CN (1) | CN102576367B (ko) |
| WO (1) | WO2011049313A2 (ko) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8805853B2 (en) * | 2009-12-25 | 2014-08-12 | Nec Corporation | Text mining system for analysis target data, a text mining method for analysis target data and a recording medium for recording analysis target data |
| CN104517106B (zh) * | 2013-09-29 | 2017-11-28 | 北大方正集团有限公司 | 一种列表识别方法与系统 |
| US9858923B2 (en) * | 2015-09-24 | 2018-01-02 | Intel Corporation | Dynamic adaptation of language models and semantic tracking for automatic speech recognition |
| EP3575987A1 (en) * | 2018-06-01 | 2019-12-04 | Fortia Financial Solutions | Extracting from a descriptive document the value of a slot associated with a target entity |
Family Cites Families (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| AU677605B2 (en) * | 1992-09-04 | 1997-05-01 | Caterpillar Inc. | Integrated authoring and translation system |
| JP2003085181A (ja) | 2001-09-07 | 2003-03-20 | Japan Science & Technology Corp | 事典システム |
| NO316480B1 (no) * | 2001-11-15 | 2004-01-26 | Forinnova As | Fremgangsmåte og system for tekstuell granskning og oppdagelse |
| CN1942877A (zh) * | 2004-03-31 | 2007-04-04 | 松下电器产业株式会社 | 信息提取系统 |
| US20060074980A1 (en) * | 2004-09-29 | 2006-04-06 | Sarkar Pte. Ltd. | System for semantically disambiguating text information |
| US8983962B2 (en) * | 2005-02-08 | 2015-03-17 | Nec Corporation | Question and answer data editing device, question and answer data editing method and question answer data editing program |
| US7376551B2 (en) * | 2005-08-01 | 2008-05-20 | Microsoft Corporation | Definition extraction |
| CN100474301C (zh) * | 2005-09-08 | 2009-04-01 | 富士通株式会社 | 基于数据挖掘获取词或词组单元译文信息的系统和方法 |
| WO2007105202A2 (en) * | 2006-03-10 | 2007-09-20 | Avraham Shpigel | Automatic reusable definitions identification (rdi) method |
| JP2007286355A (ja) | 2006-04-17 | 2007-11-01 | Masanori Fukushima | 学習支援装置および学習支援方法 |
| US7657421B2 (en) * | 2006-06-28 | 2010-02-02 | International Business Machines Corporation | System and method for identifying and defining idioms |
| KR20080037323A (ko) | 2006-10-26 | 2008-04-30 | 주식회사 문깡 | 영어학습방법 |
| US20080249764A1 (en) * | 2007-03-01 | 2008-10-09 | Microsoft Corporation | Smart Sentiment Classifier for Product Reviews |
| KR20090035346A (ko) | 2007-10-05 | 2009-04-09 | 박철 | 어휘 분석을 수행하는 어학학습 방법 |
| CN101441636A (zh) * | 2007-11-21 | 2009-05-27 | 中国科学院自动化研究所 | 一种基于知识库的医院信息搜索引擎及系统 |
| JP4654238B2 (ja) | 2007-12-26 | 2011-03-16 | みずほ情報総研株式会社 | 説明表示システム、説明表示方法及び説明表示プログラム |
| US20090327210A1 (en) * | 2008-06-27 | 2009-12-31 | Microsoft Corporation | Advanced book page classification engine and index page extraction |
| US20100063797A1 (en) * | 2008-09-09 | 2010-03-11 | Microsoft Corporation | Discovering question and answer pairs |
| US7937386B2 (en) * | 2008-12-30 | 2011-05-03 | Complyon Inc. | System, method, and apparatus for information extraction of textual documents |
-
2009
- 2009-10-23 KR KR1020090100962A patent/KR101072100B1/ko not_active Expired - Fee Related
-
2010
- 2010-10-11 JP JP2012530792A patent/JP5690829B2/ja not_active Expired - Fee Related
- 2010-10-11 CN CN201080046722.0A patent/CN102576367B/zh not_active Expired - Fee Related
- 2010-10-11 US US13/498,322 patent/US8666987B2/en active Active - Reinstated
- 2010-10-11 WO PCT/KR2010/006943 patent/WO2011049313A2/ko not_active Ceased
Also Published As
| Publication number | Publication date |
|---|---|
| KR101072100B1 (ko) | 2011-10-10 |
| KR20110044345A (ko) | 2011-04-29 |
| WO2011049313A3 (ko) | 2011-09-01 |
| WO2011049313A9 (ko) | 2011-06-30 |
| US8666987B2 (en) | 2014-03-04 |
| US20120197894A1 (en) | 2012-08-02 |
| JP5690829B2 (ja) | 2015-03-25 |
| JP2013506187A (ja) | 2013-02-21 |
| CN102576367B (zh) | 2014-09-10 |
| CN102576367A (zh) | 2012-07-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US12210832B2 (en) | Method of responding based on sentence paraphrase recognition for dialog system | |
| KR102881777B1 (ko) | 자연어처리 기반의 인공지능 모델을 이용한 faq를 자동생성하기 위한 방법 및 이를 위한 장치 | |
| CN110609983B (zh) | 一种政策文件结构化分解方法 | |
| Karim et al. | Technical challenges and design issues in bangla language processing | |
| WO2014069741A1 (ko) | 자동 채점 장치 및 방법 | |
| WO2014030834A1 (ko) | 문법의 오류 검출 방법, 이를 위한 오류검출장치 및 이 방법이 기록된 컴퓨터로 판독 가능한 기록매체 | |
| CN113449516A (zh) | 首字母缩写词的消歧方法、系统、电子设备及存储介质 | |
| US11475222B2 (en) | Automatically extending a domain taxonomy to the level of granularity present in glossaries in documents | |
| WO2011074772A2 (ko) | 문법 오류 시뮬레이션 장치 및 방법. | |
| CN119358562A (zh) | 一种英语作文评估方法及装置 | |
| WO2011049313A2 (ko) | 표현 및 설명 추출을 위한 문서 처리 장치 및 방법 | |
| Bhatti et al. | Managing contextual shifts: Pragmatics and semantics in AI dialogue systems for Pakistani language documentation | |
| CN109918677B (zh) | 一种英文单词语义解析的方法及系统 | |
| Mlambo et al. | Human language technology tools for indigenous South African languages and their potential use | |
| CN120234589A (zh) | 敏感信息识别方法、装置、服务器和计算机可读存储介质 | |
| CN111597827B (zh) | 一种提高机器翻译准确度的方法及其装置 | |
| Zhang | [Retracted] Russian Speech Conversion Algorithm Based on a Parallel Corpus and Machine Translation | |
| WO2022114325A1 (ko) | 자연어 대화에서 질문의 유사성을 분석하기 위한 질의 자질 추출 장치 및 방법 | |
| CN121579695B (zh) | 一种大模型违规语义检测方法、系统、设备及介质 | |
| Pilán | Detecting context dependence in exercise item candidates selected from corpora | |
| CN118779450A (zh) | 文本标注方法、装置、设备以及存储介质 | |
| Olagbende | Natural Language Processing (NLP) Techniques for Afan Oromo Text Analysis | |
| KR20110034797A (ko) | 문서 처리 장치 및 방법 | |
| Nyetanyane et al. | UmobiTalk: Ubiquitous Mobile Speech Based Translator for Sesotho Language | |
| WO2024181589A1 (ko) | 학습데이터를 확장하는 시스템 및 그 제공 방법 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| WWE | Wipo information: entry into national phase |
Ref document number: 201080046722.0 Country of ref document: CN |
|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 10825138 Country of ref document: EP Kind code of ref document: A1 |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 13498322 Country of ref document: US Ref document number: 2012530792 Country of ref document: JP |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 10825138 Country of ref document: EP Kind code of ref document: A2 |