人工知能学会論文誌
原著論文
対話システムが話し手役になるためのオープンドメイン独話生成
稲葉 通将吉野 友香高橋 健一
著者情報
ジャーナル フリー

31 巻 (2016) 1 号 p. DSF-F_1-9

詳細
PDFをダウンロード (843K) 発行機関連絡先
抄録

This paper presents an open domain monologue generation method for non-task-oriented dialogue systems to be able to speak their opinions and impressions as a speaker. To generate monologues, we acquire suitable utterances that contain a given topic from Twitter. Our method determines whether utterances have cohesion or not using the support vector machine and concatenate them in a row. It scores the utterance sequences from the aspect of their humor, unexpectedness and speciality in the given topic. We acquire the utterance sequences that ranks high as monologues. Results of an experiment demonstrate that our method can generate amusing and semantically appropriate monologues.

著者関連情報
© 人工知能学会 2016
前の記事 次の記事

閲覧履歴
feedback
Top