Electronics and Telecommunications Research Institute

Hyo Jung Oh

Chung Hee Lee

Myung Gil Jang

Jeong Mu Heo

Hyun Ki Kim

Mi Ran Choi

Pum Mo Ryu

Yong Jin Bae

Soo Jong Lim

Yeo Chan Yoon

Joon Ho Lim

Hyeon Jin Kim

Yoon Jae Choi

Yo Han Jo

Ji Hyun Wang

Chang Ki Lee

Sang Kyu Park

Young Jik Lee

Hyung Jik Lee

Yi Gyu Hwang

Young Rae Kim

Provided are a system and method for answering a natural language question which show improved information retrieval performance. The system includes an index unit configured to analyze text of previously stored irregular documents and classify and index the irregular documents according to meanings of sentences or paragraphs, a database configured to receive and store the irregular documents indexed according to the meanings and transmitted from the index unit, a retrieval unit configured to extract an index word by semantically analyzing an input question and search the database for documents related to the extracted index word, and a provision unit configured to generate a correct answer to the question by analyzing the documents searched by the retrieval unit and provide the search results and the correct answer.

System and method for answering natural language question

Disclosed are a method and apparatus for building information on an emotion lexicon. The method according to the disclosure may include: retrieving specific documents on the basis of a specific emotion expression lexeme to derive emotion basis lexemes of the emotion expression lexeme from sentences including the emotion expression lexeme; and deriving a new emotion basis lexeme determined among the derived emotion basis lexemes according to at least one predefined new lexeme criterion and then storing the new emotion basis lexeme in an emotion lexicon. The method may include writing emotion expression lexemes associated to the emotion basis lexemes and assigning an emotion strength to them by multiplying an emotion strength value associated with an emotion expression lexeme and a sum of weights associated with a plurality of modifiers of emotion expression lexemes.

Method and apparatus for building emotion basis lexeme information on an emotion lexicon comprising calculation of an emotion strength for each lexeme

Disclosed are a question answering system for structured knowledgebase using deep natural language question analysis, and a method thereof, the question answering system for structured knowledgebase using deep natural language question analysis includes a deep natural language question analysis unit configured to create a structure of a semantic frame by analyzing a natural language question that is input, a question-intermediate expression creation unit configured to create a question-intermediate expression of a lexicon level based on the semantic frame, a knowledgebase-specialized query creation unit configured to create a query used to search in knowledgebase that is a subject of search, based on the question-intermediate expression, and a knowledgebase search unit configured to find a correct answer in the knowledgebase that is subject of search based on the query, to provide an accuracy of the correct answer, a confidence of the correct answer and an evidence for the correct answer.

Question answering system and method for structured knowledgebase using deep natural language question analysis

A natural language question answering system and method, and a paraphrase module are provided. The natural language question answering system includes a conversion module configured to generate a plurality of modified questions by paraphrasing a user's question; a plurality of question answering engines configured to receive each of the user's question and the modified questions, and select candidate answers corresponding to each of the user's question and the modified questions; and a detection module configured to detect at least one among the selected candidate answers as an answer.

Natural language question answering system and method, and paraphrase module

Disclosed are an apparatus, a system, and a method for searching for a power user in social media. The apparatus according to the present invention includes an input unit configured to receive a keyword corresponding to an interested object from a user; a communication unit configured to transmit a search request message including the received keyword and receive a search response message corresponding to the transmitted search request message; a controller configured to, when receiving the search response message, extract a search list in which power users related to the keyword are arranged according to a preset power ranking from the received search response message; a display unit configured to sequentially display the power users related to the keyword received from the user according to the preset power ranking based on the extracted search list; and a storage unit configured to store the extracted search list.

Apparatus, system, and method for searching for power user in social media

Disclosed are an apparatus, a system, and a method for detecting complex issues based on social media analysis according to the present invention. A system for detecting complex issues based on social media analysis according to the present invention includes: a unit issue detecting unit configured to receive a keyword from a user terminal, and to detect per-type unit issues associated with the received keyword; a complex issue detecting unit configured to detect per-type complex issues from the detected per-type unit issues; a complex issue ranking unit configured to analyze the detected per-type complex issues, and to rank the per-type complex issues based on the analysis result; and a complex issue configuring unit configured to configure the ranked per-type complex issues in a predetermined form that enable users to induce a micro trend, and to provide the configured form to a user.

Apparatus, system, and method for detecting complex issues based on social media analysis

The present invention relates to a social media question and answer service, and discloses a social media issue processing device and method. The method includes a question analyzing unit which analyzes a question type of an input question through a question pattern dictionary which is stored in advance; a social media analyzing unit which performs issue period recognition for the question, question type based analysis, question based summary creation, and question based reliability calculation; and a report creating unit which creates a summary in accordance with at least one of correlation between the question type and the question based summary, correlation between the issue period and the question type based analysis result, and correlation between the reliability and the question based summary.

Processing method for social media issue and server device supporting the same

Provided are an apparatus and method for post-processing a dialogue error in a speech dialogue system using multilevel verification, in which both of a user's current utterance and a whole dialogue flow are taken into account through the multilevel verification including speech recognition results analysis, linguistic analysis, discourse analysis and dialogue analysis. As a result, various errors that may occur in the speech dialogue system are detected, and error post-processing appropriate to a detected error type is performed, so that speech recognition errors may be reduced.

Apparatus and method for post-processing dialogue error in speech dialogue system using multilevel verification

An apparatus and method for efficiently constructing learning data required in statistical methodology used in information retrieval, information extraction, translation, natural language processing, etc. are provided. The method includes the steps of: generating learning models by performing machine learning with respect to learning data; attaching tags to a raw corpus automatically by using the generated learning models to thereby generate learning data candidates; calculating confidence scores of the generated learning data candidates, and then selecting a learning data candidate using the confidence scores; and allowing a user to correct an error in the selected learning data candidate through an interface and adding the error-corrected learning data candidate to the learning data, thereby adding new learning models incrementally.

Growing community of inventors

Daejeon, South Korea

Hyo Jung Oh