Host: The Japanese Society for Artificial Intelligence
Name : The 33rd Annual Conference of the Japanese Society for Artificial Intelligence, 2019
Number : 33
Location : [in Japanese]
Date : June 04, 2019 - June 07, 2019
Trivia has characteristics that draw people's interests and has been used as a strategy for attracting interests in contents in various conversational applications, such as entertainment and educational sites. In this paper, we propose a model that distinguishes trivia based on the surface representation of sentences. We incorporated the trivia presentation function into the spoken dialogue system we are developing and assessed the effect of presenting trivia in the introduction part of the topics in the news transmission task. As a result of the experiment, we confirmed that it is effective for enhancing users' interests in topics and promoting the feeling of rapport with system although we were not able to find significant improvements in the number of users' feedback and the Efficiency of Information Transfer (EoIT).