Shohei Fujikura
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. Experimental results indicate that high-incongruity replies are significantly effective against low-incongruity replies with a limited condition.
- Higashinaka, R., Imamura, K., Meguro, T., Miyazaki, C., Kobayashi, N., Sugiyama, H., Hirano, T., Makino, T., and Matsuo, Y. Towards an open-domain conversational system fully based on natural language processing. In Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers (2014), 928--939.Google Scholar
- Kao, J., Levy, R., and Goodman, N. The funny thing about incongruity: A computational model of humor in puns. In Proceedings of the 35th Annual Conference of the Cognitive Science Society (2013), 728--733.Google Scholar
- Miyazawa, K., Tokoyo, T., Masui, Y., Matsuo, N., and Kikuchi, H. Factors of interaction in the spoken dialogue system with high desire of sustainability (in japanese). The Transactions of the Institute of Electronics, Information and Communication Engineers. A 95, 1 (2012), 27--36.Google Scholar
- Suls, J. M. A two-stage model for the appreciation of jokes and cartoons: An information-processing analysis. In The psychology of humor: Theoretical perspective and empirical issues, J. H. Goldstein and P. E. McGhee, Eds. New York: Academic Press, 1972, 81--100.Google Scholar
- Tomohide S., Y. E., and K., S. Chat-like conversational system based on selection of reply generating module with reinforcement learning. In Proceedings of the 5th International Workshop Series on Spoken Dialog Systems (IWSDS2014) (Napa, California, 2014), 124--129.Google Scholar
- Ue, H. The development of a sense of humor scale (in japanese). Journal of Kansai University of Welfare Sciences 11 (2008), 31--40.Google Scholar
Index Terms
- Humor Utterance Generation for Non-task-oriented Dialogue Systems
Recommendations
BERT-based response selection in dialogue systems using utterance attention mechanisms
Highlights- BERT-based response selection in dialogue systems.
- Utterance attention to ...
AbstractDialogue systems, one of the core research fields of natural language processing, attempt to understand the utterances of a user and generate an appropriate response. Response selection in a retrieval-based dialogue system involves ...
Turn-yielding cues in task-oriented dialogue
SIGDIAL '09: Proceedings of the SIGDIAL 2009 Conference: The 10th Annual Meeting of the Special Interest Group on Discourse and DialogueWe examine a number of objective, automatically computable TURN-YIELDING CUES --- distinct prosodic, acoustic and syntactic events in a speaker's speech that tend to precede a smooth turn exchange --- in the Columbia Games Corpus, a large corpus of task-...
Comments