主催: 人工知能学会
会議名: 第75回 言語・音声理解と対話処理研究会
回次: 75
開催地: 早稲田大学 喜久井町キャンパス 40号館 グリーン・コンピューティング・システム研究開発センター
開催日: 2015/10/29 - 2015/10/30
p. 08-
It is difficult to detect a breakdown phenomena in the dialogue with a chat-oriented dialogue system because of the variety of causes of breakdown. To deal with this problem, we analyzed a chat dialogue corpus and made a taxonomy of the errors that yield the dialogue break-down. In this paper, we propose a breakdown detection method that consists of combinations of the classifiers for the different cause of errors based on the taxonomy.