National Institute of Information and Communications Technology, Incorporated

National Institute of Information and Communications Technology, Independent Administrative Institution

Hitoshi Isahara

Kiyotaka Uchimoto

Masaki Murata

Norio Fujimaki

Tomoe Hayakawa

Kyouko Kanzaki

Mika Shindo

Satoshi Sekine

By inputting words of source language as a keyword (), a translation pairs are extracted () from a parallel corpus database including source language and target one. From the partially corresponding information on the translation sentence, a corresponding phrase group table formed by the corresponding phase of the target language corresponding to the source language phrase including a keyword phrase f the source language is stored (). Text generator () assumes a relationship between the phrases of different language contained in the corresponding phrase group table and generates a text sentence candidate () of the target language.

Method for generating a text sentence in a target language and text sentence generating apparatus

A device or computer readable medium for accurately and automatically obtaining general-purpose information regarding the usage difference between a plurality of synonyms and quasi-synonyms, such as the types of words with which the synonyms and quasi-synonyms are often used, is described. The usage information may be obtained by receiving the input of a plurality of words; extracting sentence data including an inputted word from a corpus; analyzing the sentence structure of the sentence data and extracting nouns that are in a grammatical relationship with the inputted word included in the sentence data; extracting the nodes representing the nouns and the nodes representing the semantic category of the noun from a thesaurus and forming a directional graph for each inputted word; comparing a plurality of directional graphs and extracting the difference nodes; and outputting the extracted difference nodes as information relating to the usage difference of the inputted words.

Word usage analyzer

The device of the present invention can automatically extract words under accurately controlled set conditions. A word presenting means presents words to a subject, a biological activity measuring means measures the biological activity in the subject, and a calculation means receives a biological activity signal from the biological activity measuring means and calculates time from presenting the words until detecting a biological activity by the subject accompanied with the word. The calculation means is equipped with a word database where word data indicating words are stored and can be presented to the subject, a category data of the words and attribute data of the words are related and also stored, respectively, and a word extractor to search the word database and to extract the word data belonging to or relating to a predetermined category, and, satisfying predetermined word attribute, based upon the search conditions. The word presenting means presents a portion of or entire words indicated by the word data extracted by the word presenting means to the subject.

Language processing function measuring device

A text generation method and a text generation device generate a meaningful text even though the number of input keywords is insufficient. In order to achieve this object, keywords are input to the text generation device. In the text generation device, a Bunsetsu-generation-rule acquisition unit acquires a Bunsetsu generation rule from a corpus and a Bunsetsu-candidate generation unit generates Bunsetsu candidates from the keywords. A text candidate generation unit generates text candidates with assuming a dependency relation among the Bunsetsu candidates. An evaluation unit evaluates the text candidates and outputs text in accordance with the evaluation.

Text generation method and text generation device

An negative example prediction processing method for predicting a likelihood of examples being negative for data where, with respect to a certain problem, it is not known whether the data is for a correctly worded positive example or for an incorrectly worded negative example. In this negative example prediction processing method, an unknown example x is inputted and a determination is made as to whether or not the example x exists in a positive example database provided in advance. If the example x does not exist, a typical probability of appearance p(x) for the example x is calculated, and a likelihood Q (x) of the example x being an negative example is calculated from the probability of appearance p(x).

Growing community of inventors

Tokyo, Japan

Hitoshi Isahara