Role play-based question-answering by real users for building chatbots with consistent personalities
| Autor: | Hidetoshi Kawabata, Noritake Adachi, Emi Yamaguchi, Ryuichiro Higashinaka, Masahiro Mizukami, Junji Tomita |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
030507 speech-language pathology & audiology
03 medical and health sciences Character (mathematics) Computer science Human–computer interaction Question answering 010501 environmental sciences 0305 other medical science Personality psychology 01 natural sciences 0105 earth and related environmental sciences |
| Zdroj: | SIGDIAL Conference |
| DOI: | 10.18653/v1/w18-5031 |
| Popis: | Having consistent personalities is important for chatbots if we want them to be believable. Typically, many question-answer pairs are prepared by hand for achieving consistent responses; however, the creation of such pairs is costly. In this study, our goal is to collect a large number of question-answer pairs for a particular character by using role play-based question-answering in which multiple users play the roles of certain characters and respond to questions by online users. Focusing on two famous characters, we conducted a large-scale experiment to collect question-answer pairs by using real users. We evaluated the effectiveness of role play-based question-answering and found that, by using our proposed method, the collected pairs lead to good-quality chatbots that exhibit consistent personalities. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|