Conversational Response Re-ranking Based on Entrainment Prediction
-
- KANEZAKI Shota
- Doshisha University, Graduate School of Science and Engineering Guardian Robot Project, RIKEN
-
- KAWANO Seiya
- Guardian Robot Project, RIKEN
-
- YUGUCHI Akishige
- Guardian Robot Project, RIKEN
-
- KATSURAI Marie
- Doshisha University, Faculty of Science and Engineering
-
- YOSHINO Koichiro
- Guardian Robot Project, RIKEN
Bibliographic Information
- Other Title
-
- エントレインメント予測に基づいたニューラル雑談対話モデルの応答リランキング
Abstract
<p>Entrainment is a phenomenon observed in human-human conversation, which is a synchronization of speaking style according to dialogue progress. In this study, we propose a method to build an entrainable chitchat system by predicting the ideal entrainment score for the given dialogue history. The proposed method reranks existing neural conversation model outputs based on the predicted entrainment score. We conducted automatic and human-subjective evaluations to investigate the effect of the proposed method by comparing it with the system response without using the reranking system. The experimental results showed that our proposed method achieves ideal entrainment while maintaining the naturalness of the generated responses compared to the baseline method.</p>
Journal
-
- Proceedings of the Annual Conference of JSAI
-
Proceedings of the Annual Conference of JSAI JSAI2022 (0), 3Yin248-3Yin248, 2022
The Japanese Society for Artificial Intelligence
- Tweet
Details 詳細情報について
-
- CRID
- 1390011231094516608
-
- Text Lang
- ja
-
- Data Source
-
- JaLC
-
- Abstract License Flag
- Disallowed