| Presentation # | 9 |
| Session: | Dialogue |
| Location: | Kallirhoe Hall |
| Session Time: | Thursday, December 20, 10:00 - 12:00 |
| Presentation Time: | Thursday, December 20, 10:00 - 12:00 |
| Presentation: |
Poster
|
| Topic: |
Spoken dialog systems: |
| Paper Title: |
Optimizing neural response generator with emotional impact information |
| Authors: |
Nurul Lubis, Sakriani Sakti, Koichiro Yoshino, Satoshi Nakamura, Nara Institute of Science and Technology, Japan |
| Abstract: |
The potential of dialogue systems to address user's emotional need has steadily grown. In particular, we focus on dialogue systems application to promote positive emotional states, an attempt to imitate emotional support between humans. Positive emotion elicitation takes form as chat-based dialogue interactions that is layered with an implicit goal to improve user's emotional state. To this date, existing approaches have only relied on mimicking the target responses without considering their emotional impact, i.e., the change of emotional state they cause on the listener, in the model itself. In this paper, we propose explicitly utilizing emotional impact information to optimize neural dialogue system towards generating responses that elicit positive emotion. We examine two emotion-rich corpora collected in different scenarios: Wizard-of-Oz and spontaneous. Evaluation shows that the proposed method yields lower perplexity, as well as produces responses that are perceived as more natural and likely to elicit a more positive emotion. |