Paper: An Affect-Enriched Dialogue Act Classification Model for Task-Oriented Dialogue

ACL ID P11-1119
Title An Affect-Enriched Dialogue Act Classification Model for Task-Oriented Dialogue
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2011
Authors

Dialogue act clasification is a central chal- lenge for dialogue systems. Although the im- portance of emotion in human dialogue is widely recognized, most dialogue act clasifi- cation models make limited or no use of affec- tive channels in dialogue act classification. This paper presents a novel afect-enriched dialogue act clasifier for task-oriented dia- logue that models facial expressions of users, in particular, facial expresions related to con- fusion. The findings indicate that the afect- enriched classifiers perform significantly bet- ter for distinguishing user requests for fed- back and grounding dialogue acts within textual dialogue. The results point to ways in which dialogue systems can effectively lever- age affective channels to improve dialogue act classification. ...