Nippon Telegraph and Telephone Corporation

Osaka University

Hiromi Narimatsu

Hiroaki Sugiyama

Hiroshi Ishiguro

Yuichiro Yoshikawa

Tsunehiro Arimoto

Takamasa Iio

Masahiro Mizukami

Provided is a technique for generating a tagging model for attaching a tag in consideration of a phrase based on dependency between words. A tagging model generation apparatus includes a learning sectionwhich generates, by using inputted learning data, a tagging model including probability-related information serving as information related to the probability that each tag is associated with each word-related information, and joint probability-related information serving as information related to a joint probability which serves as the probability of appearance of each tag in which appearance frequencies of a plurality of consecutive tags associated with pieces of word-related information of a plurality of consecutive words in each text are taken into consideration, and a storage sectionwhich stores the generated tagging model.

Tag assignment model generation apparatus, tag assignment apparatus, methods and programs therefor using probability of a plurality of consecutive tags in predetermined order

It is an object of the present invention to promote a user's understanding or agreement, and to cause a dialogue to last long. A dialogue systemconducts a dialogue with a user. A humanoid robot-presents a first utterance which is a certain utterance. When the userperforms an action indicating that the user cannot understand the first utterance or it is predicted that the user performs an action indicating that the user cannot understand the first utterance or when the user does not perform any action indicating that the user can understand the first utterance, or it is predicted that the user will not perform any action indicating that the user can understand the first utterance, then the humanoid robot-presents a second utterance which is at least one utterance resulting from paraphrasing the contents of the first utterance.

Dialogue method, dialogue system, dialogue apparatus and program

It is an object of the present invention to prevent inattentive listening to a dialogue of an agent without taking it seriously and to make it easier to understand the dialogue with the agent. A dialogue systemconducts a dialogue with a user. A humanoid robot-presents a leap-in-logic utterance, which is an utterance, of which a logical structure is partially missing. The userexpresses a confirmation action which is an action confirming the missing information in the leap-in-logic utterance. The humanoid robot-presents a supplementary utterance which is an utterance describing the missing information.

It is an object of the present invention to induce a dialogue to a topic that a dialogue system tries to present. A dialogue systempresents a first utterance which is a certain utterance and a target utterance related to the first utterance to a user. A humanoid robot-presents the first utterance. A microphone-receives a user utterance of the userafter the first utterance. A humanoid robot-presents at least one topic-inducing utterance for inducing the topic to the target utterance based on a recognition result of the user utterance and an utterance sentence of the target utterance after the user utterance. The humanoid robot-presents the target utterance after the topic-inducing utterance.

It is an object of the present invention to provide a dialog technique that can reduce a user's uncomfortable feeling. A dialog systemis a dialog system that conducts a dialog with the user, the dialog system including a presentation partthat presents an action to fill a gap between a user utterance and a response utterance of the dialog system, after it is estimated or determined that the user utterance has ended or after a predicted time at which the user utterance ends, and before the dialog system makes a response utterance to the user utterance.

Growing community of inventors

Soraku-gun, Japan

Hiromi Narimatsu