Humor utterance generation for non-task-oriented dialogue systems

Shohei Fujikura; Yoshito Ogawa; Hideaki Kikuchi

doi:10.1145/2814940.2814966

Humor utterance generation for non-task-oriented dialogue systems

Shohei Fujikura, Yoshito Ogawa, Hideaki Kikuchi

School of Human Sciences

Research output: Chapter in Book/Report/Conference proceeding › Conference 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 language	English
Title of host publication	HAI 2015 - Proceedings of the 3rd International Conference on Human-Agent Interaction
Publisher	Association for Computing Machinery, Inc
Pages	171-173
Number of pages	3
ISBN (Electronic)	9781450335270
DOIs	https://doi.org/10.1145/2814940.2814966
Publication status	Published - 2015 Oct 21
Event	3rd International Conference on Human-Agent Interaction, HAI 2015 - Daegu, Korea, Republic of Duration: 2015 Oct 21 → 2015 Oct 24

Publication series

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

Other

Other	3rd International Conference on Human-Agent Interaction, HAI 2015
Country/Territory	Korea, Republic of
City	Daegu
Period	15/10/21 → 15/10/24

Keywords

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

ASJC Scopus subject areas

Human-Computer Interaction
Artificial Intelligence
Software

Access to Document

10.1145/2814940.2814966

Cite this

Fujikura, S., Ogawa, Y., & Kikuchi, H. (2015). Humor utterance generation for non-task-oriented dialogue systems. In HAI 2015 - Proceedings of the 3rd International Conference on Human-Agent Interaction (pp. 171-173). (HAI 2015 - Proceedings of the 3rd International Conference on Human-Agent Interaction). Association for Computing Machinery, Inc. https://doi.org/10.1145/2814940.2814966

Humor utterance generation for non-task-oriented dialogue systems. / Fujikura, Shohei; Ogawa, Yoshito; Kikuchi, Hideaki.
HAI 2015 - Proceedings of the 3rd International Conference on Human-Agent Interaction. Association for Computing Machinery, Inc, 2015. p. 171-173 (HAI 2015 - Proceedings of the 3rd International Conference on Human-Agent Interaction).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Fujikura, S, Ogawa, Y & Kikuchi, H 2015, Humor utterance generation for non-task-oriented dialogue systems. in HAI 2015 - Proceedings of the 3rd International Conference on Human-Agent Interaction. HAI 2015 - Proceedings of the 3rd International Conference on Human-Agent Interaction, Association for Computing Machinery, Inc, pp. 171-173, 3rd International Conference on Human-Agent Interaction, HAI 2015, Daegu, Korea, Republic of, 15/10/21. https://doi.org/10.1145/2814940.2814966

@inproceedings{2bd1bdde74e748a9a5b222869479206a,

title = "Humor utterance generation for non-task-oriented dialogue systems",

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.",

keywords = "Desire of continuing dialogue, Dialogue system, Humor generation, Non-task-oriented",

author = "Shohei Fujikura and Yoshito Ogawa and Hideaki Kikuchi",

note = "Publisher Copyright: {\textcopyright} 2015 ACM. Copyright: Copyright 2017 Elsevier B.V., All rights reserved.; 3rd International Conference on Human-Agent Interaction, HAI 2015 ; Conference date: 21-10-2015 Through 24-10-2015",

year = "2015",

month = oct,

day = "21",

doi = "10.1145/2814940.2814966",

language = "English",

series = "HAI 2015 - Proceedings of the 3rd International Conference on Human-Agent Interaction",

publisher = "Association for Computing Machinery, Inc",

pages = "171--173",

booktitle = "HAI 2015 - Proceedings of the 3rd International Conference on Human-Agent Interaction",

}

TY - GEN

T1 - Humor utterance generation for non-task-oriented dialogue systems

AU - Fujikura, Shohei

AU - Ogawa, Yoshito

AU - Kikuchi, Hideaki

PY - 2015/10/21

Y1 - 2015/10/21

N2 - 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.

AB - 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.

KW - Desire of continuing dialogue

KW - Dialogue system

KW - Humor generation

KW - Non-task-oriented

UR - http://www.scopus.com/inward/record.url?scp=84962905808&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84962905808&partnerID=8YFLogxK

U2 - 10.1145/2814940.2814966

DO - 10.1145/2814940.2814966

M3 - Conference contribution

AN - SCOPUS:84962905808

T3 - HAI 2015 - Proceedings of the 3rd International Conference on Human-Agent Interaction

SP - 171

EP - 173

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

PB - Association for Computing Machinery, Inc

T2 - 3rd International Conference on Human-Agent Interaction, HAI 2015

Y2 - 21 October 2015 through 24 October 2015

ER -

Humor utterance generation for non-task-oriented dialogue systems

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Cite this