International Business Machines Corporation

Akihiro Kosugi

Akira Koseki

Masaki Ono

Toshiro Takase

Atsushi Sato

Hiroshi Kanayama

Tatsuya Sobue

Kentarou Fukuda

Norimasa Hayashida

A computer-implemented method is presented for building a topic model to discover topics in a collection of documents generated by a plurality of users. The method includes extracting conversations from the collection of documents, dividing the extracted conversations into a plurality of segments, generating a topic distribution for each of the plurality of segments based on the extracted conversations and a first pre-defined prior probability distribution, and generating continuous value constructs for each of the topic distributions based on an external corpus and a second pre-defined prior probability distribution, wherein similarity is defined between the continuous value constructs.

Interactively building a topic model employing semantic similarity in a spoken dialog system

A computer-implemented method for generating a control signal for a tele-presence robot by a computing device based on a movement of an operator, the method includes calculating a direction where at least part of the operator is positioned based on a camera acquiring an image of the at least part of the operator; calculating an orientation where the at least part of the operator points; and generating at least one motion parameters of the tele-presence robot as the control signal based on the direction in combination with the orientation, wherein the direction and the orientation are reflected to the at least one motion parameters differently.

Generating control signal for tele-presence robot

A method, a computer system, and a computer program product are provided for calculating a degree of similarity of users. Each user may be a preparer and an answerer of one or more quizzes. The method includes collecting one or more quizzes from one or more users as preparers and providing the collected quizzes to one or more user as answerers. The method further includes collecting one or more answering activities of one or more answerers to the provided quizzes from the one or more answerers, wherein a pair includes a preparer and an answerer. The method additionally includes calculating, for each pair, a degree of similarity of knowledge background, based on the one or more answering activities of the one or more answerers.

Calculation of a degree of similarity of users

In a client, an input receiver receives utterance data inputted through the client and utterance data inputted through a different client and received by a receiver, and then stores the utterance data in a past log storage as a past log. When the input receiver receives new utterance data, a reference information generator determines preceding utterance data referred to by the new utterance data, from the past log, generates reference information indicating a reference relationship, and then stores the reference information in a reference information storage. Then, a transmitter transmits the new utterance data and the reference information to the different client, and a display controller displays the utterance data stored as the past log, the new utterance data, and an indicator based on the reference information.

Growing community of inventors

Tokyo, Japan

Akihiro Kosugi