Humor utterance generation for non-task-oriented dialogue systems

Shohei Fujikura, Yoshito Ogawa, Hideaki Kikuchi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We propose a humor utterance generation method that is compatible with dialogue systems, to increase "desire of continuing dialogue". A dialogue system retrieves leading-item: noun pairs from Twitter as knowledge and attempts to select the most humorous reply using word similarity, which reveals that incongruity can be explained by the incongruity-resolution model. We consider the differences among individuals, and confirm the validity of the proposed method. Ex-perimental results indicate that high-incongruity replies are significantly effective against low-incongruity replies with a limited condition.

Original languageEnglish
Title of host publicationHAI 2015 - Proceedings of the 3rd International Conference on Human-Agent Interaction
PublisherAssociation for Computing Machinery, Inc
Pages171-173
Number of pages3
ISBN (Electronic)9781450335270
DOIs
Publication statusPublished - 2015 Oct 21
Event3rd International Conference on Human-Agent Interaction, HAI 2015 - Daegu, Korea, Republic of
Duration: 2015 Oct 212015 Oct 24

Publication series

NameHAI 2015 - Proceedings of the 3rd International Conference on Human-Agent Interaction

Other

Other3rd International Conference on Human-Agent Interaction, HAI 2015
CountryKorea, Republic of
CityDaegu
Period15/10/2115/10/24

Keywords

  • Desire of continuing dialogue
  • Dialogue system
  • Humor generation
  • Non-task-oriented

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Artificial Intelligence
  • Software

Cite this