用例に基づく疑似的な聞き間違いによりユーモア表現を生成する対話システム

Dialogue systems, which give users quick and easy access to required information interactively, have been widely used in various fields. Dialogue systems equipped with interfaces (e.g., humanoid robots and anthropomorphic agents) have been developed in order to enhance familiarity and dialogue continuity. Related studies, in which interactive agents generate humor expressions, have also been reported. Humor is indispensable for the formation of friendly relationships between people and systems, and humor expressions can be applied in situations that generate familiar responses and provide fun to users. In this study, in order to evoke humor through dialogue, a method to generate humorous expression by asking again due to pseudo mishearing of a part of users’ queries based on examples is proposed. Specifically, a conversion candidate dictionary for humor expressions, based on Wikipedia of Japanese edition and a classification vocabulary table in which words are classified semantically, is created by word completion using distributed representation. In addition, a word conversion method is designed by approximately 1,000 mishearing survey from Twitter, and the function based on the proposed method is implemented in a dialogue system introduced into a university as a model case. In the results of the comparative evaluation with other methods quantitatively, the proposed methods gave users the most humor by converting singular and multiple words. Thus, the effectiveness of the proposed method was clarified.

ここに掲載した著作物の利用に関する注意 本著作物の著作権は人工知能学会に帰属します。本著作物は著作権者である人工知能学会の許可のもとに掲載するものです。ご利用に当たっては「著作権法」に従うことをお願いいたします。
Notice for the use of this material. The copyright of this material is retained by the Japanese Society for Artificial Intelligence (JSAI). This material is published on this web site with the agreement of the author(s) and the JSAI. Please be complied with Copyright Law of Japan if any users wish to reproduce, make derivative work, distribute or make available to the public any part or whole thereof. All Rights Reserved, Copyright (C) The Japanese Society for Artificial Intelligence.