Nec Corporation

Susumu Akamine

Kai Ishikawa

Kenji Satoh

Takashi Onishi

Shinichi Ando

Satoshi Nakazawa

Masaaki Tsuchida

Kosuke Yamamoto

Kazunori Muraki

Toshio Takeda

Yousuke Sakao

A text visualization system allows a user to ascertain a relationship of viewpoints between categories in clustering of documents including texts of a plurality of categories. Each of a plurality of documents includes texts of each of a plurality of categories. A text and an element text that entails the text among texts included in the plurality of documents are set with respect to each of the categories. A text display displays a plurality of texts of each of one or more categories among the plurality of categories. The text display, in response to receiving a designation of a text of a specific category by a reception unit, extracts, from a plurality of texts of another category, a text that entails an element text of the another category included in a document including an element text that entails the text of the specific category, and displays the extracted text.

Text visualization system, text visualization method, and recording medium

A question-answering device, a question-answering method, and a question-answering program that can obtain an answer to an inputted query with high probability are described. A score calculation elementdetermines a matching degree between the group of the style and the topic of an inputted query and the group of the style and the topic of the query of question-answer pairs. A search result presentation elementnarrows the question-answer pairs on the basis of the matching degree.

Question answering device, question answering method, and question answering program

Language analysis meansanalyzes texts read from a text DB, and generates a sentence structure as the analysis result. Similar-structure generation adjustment meansgenerates, from an input of an input device, a determination item for determining whether or not the structures are identical every type of differences between the sentence structures. Similar-structure determination adjustment meansgenerates, from an input of the input device, a determination item for determining whether or not the difference between attribute values is ignored every type of attribute values. Similar-structure generating meansgenerates a similar structure of a partial structure forming the sentence structure obtained by language analysis meansin accordance with the determination item from the similar-structure generation adjustment means, and sets the generated similar structure as an equivalent class of the partial structure on the generation source. Frequent-similar-pattern detection meansignores the attribute value in accordance with the determination item given from the similar-structure determination adjustment means, detects the frequent pattern on the basis of a set of equivalent classes from the similar-structure generating means, and outputs the frequent pattern to an output device

Text mining device, method thereof, and program

A request content identification system performs an audio recognition process according to audio data inputted from an input device () and performs a request analysis process by using a common rule stored in common rule storage means () and a request unique rule stored in request unique rule storage means (). Moreover, the request content identification system performs a similar document search process between the audio recognition result and an information request sentence or a reply stored in replay request data storage means (). Request candidate score calculation means () calculates an integrated score from an audio recognition score, a request analysis score, and a similar document search score obtained by the respective processes. Request identification result generation means () identifies the request content having the highest integrated score and sends it to an output device ().

Request content identification system, request content identification method using natural language, and program

A system includes a time-series data pattern checking means that receives time-series data from an input device and extracts a time-series pattern corresponding to the received time-series, and an effective period determination means that extracts an effective period corresponding to the time-series pattern from a time-series pattern/effective period correspondence table stored in a time-series pattern/effective period correspondence table storage means. The effective period determination means determines effective period time-series data which is a portion of the time-series data received from the input device in the effective period, according to the determined effective period and causes an output device to outputs the determined effective period and the determined effective period time-series data.

Information analysis system, information analysis method, and information analysis program

A paraphrase model of a question text inputted by a user is learned, and a paraphrase expression is generated in real time. When information in text set storage unit is updated, text pair extracting unit extracts a paraphrase text pair from the text set storage unit and stores it in text pair storage unit. Model learning unit learns a question text paraphrase model from the paraphrase text pair in text pair storage unit, and stores it in model storage unit. Text pair extracting unit extracts a paraphrase text pair again from the text set storage unit by using the question text paraphrase model which the model storage unit possesses, and stores it in the text pair storage unit. In case where the stored paraphrase text pair is the same as the paraphrase text pair stored in the text pair storage unit, learning of the question text paraphrase model is ended. Candidate creating unit reads the question text paraphrase model from the model storage unit and generates a paraphrase candidate of the inputted question text.

Text paraphrasing method and program, conversion rule computing method and program, and text paraphrasing system

A system which allows utilization of retrieval terms used in retrievals performed formerly by an outsider to facilitate and accelerate retrieval of documents. A history storage apparatus stores retrieval histories each having information including a group of retrieval items including at least an item of 'retrieving person', retrieval terms and a retrieval result. A history storage section stores, when retrieval of documents is performed, a retrieval history regarding the retrieval into the history storage apparatus. A history retrieval section retrieves, in 'retrieval which is performed utilizing a retrieval history', a retrieval history which satisfies designations of terms of an inputted retrieval item from among the retrieval histories by another retrieving person stored in the retrieval storage apparatus. A retrieval section retrieves documents utilizing retrieval terms of a retrieval history by the other retrieving person detected by the history retrieval section.

Growing community of inventors

Tokyo, Japan

Susumu Akamine