{"title":"Humor Utterance Generation for Non-task-oriented Dialogue Systems","authors":"Shohei Fujikura, Yoshito Ogawa, H. Kikuchi","doi":"10.1145/2814940.2814966","DOIUrl":null,"url":null,"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.","PeriodicalId":427567,"journal":{"name":"Proceedings of the 3rd International Conference on Human-Agent Interaction","volume":"352 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2015-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 3rd International Conference on Human-Agent Interaction","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/2814940.2814966","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1
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.
京公网安备 11010802042870号
京ICP备2023020795号-1
分享
求助内容：
应助结果提醒方式：
扫码关注我们
