Nippon Telegraph and Telephone Corporation

Kuniko Saito

Junji Tomita

Nozomi Kobayashi

Atsushi Otsuka

Taichi Katayama

Ko Mitsuda

To make it possible to generate dialogue data for generating a question sentence to deeply delve conversation at a low cost. For each of a plurality of pieces of data each including a set of a first utterance sentence that is a sentence uttered by a first user, a second utterance sentence that is a sentence uttered by a second user and is a response to the first utterance sentence, and a third utterance sentence that is a sentence uttered by the first user and is a response to the second utterance sentence, a dialogue data generation unitgenerates a set of the first utterance sentence of the data and the second utterance sentence of the data as dialogue data when the second utterance sentence of the data is a question sentence using an interrogative.

Dialogue data generation device, dialogue data generation method, and program

It is an object to successfully absorb a difference in characteristics to be taken into consideration between languages and implement common named entity extraction in a processing system. A language characteristic extraction deviceincludes a language characteristic extraction unit that selects an abstract rule corresponding to a characteristic of a target language from among a collection of abstract rules common to a plurality of languages and sets, as a language-specific characteristic extraction rule, a concrete feature extraction method suited to the target language and a definition given as an output condition, defines, for each of a plurality of target languages, the language-specific characteristic extraction rule, and extracts a feature corresponding to a language of an input sentence from a morphological analysis result of the input sentence while referring to the language-specific characteristic extraction rule defined for the language and aimed at extracting a feature related to a representation or a part of speech included in the morphological analysis result and outputs the feature as a language characteristic extraction result.

Language characteristic extraction device, named entity extraction device, extraction method, and program

To make it possible to generate a response sentence with respect to an input speech sentence without preparing a large amount of data. A response-type determining unitdetermines, based on an analysis result of a speech sentence analyzed by a speech-content analyzing unit, a speech type indicating a type of the speech sentence and determines a response type with respect to the determined speech type based on the speech type and a type conversion rule prescribing, for each speech type, a rule for a response type with respect to a speech of the speech type. A response-sentence generating unitgenerates the response sentence based on the response type and a response sentence database.

Growing community of inventors

Tokyo, Japan

Kuniko Saito