Is a Knowledge-based Response Engaging?: An Analysis on Knowledge-Grounded Dialogue with Information Source Annotation
Takashi Kodama, Hirokazu Kiyomaru, Yin Jou Huang, Taro Okahisa, Sadao Kurohashi
Abstract
Currently, most knowledge-grounded dialogue response generation models focus on reflecting given external knowledge. However, even when conveying external knowledge, humans integrate their own knowledge, experiences, and opinions with external knowledge to make their utterances engaging. In this study, we analyze such human behavior by annotating the utterances in an existing knowledge-grounded dialogue corpus. Each entity in the corpus is annotated with its information source, either derived from external knowledge (database-derived) or the speaker’s own knowledge, experiences, and opinions (speaker-derived). Our analysis shows that the presence of speaker-derived information in the utterance improves dialogue engagingness. We also confirm that responses generated by an existing model, which is trained to reflect the given knowledge, cannot include speaker-derived information in responses as often as humans do.- Anthology ID:
- 2023.acl-srw.34
- Volume:
- Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 237–243
- Language:
- URL:
- https://aclanthology.org/2023.acl-srw.34
- DOI:
- Cite (ACL):
- Takashi Kodama, Hirokazu Kiyomaru, Yin Jou Huang, Taro Okahisa, and Sadao Kurohashi. 2023. Is a Knowledge-based Response Engaging?: An Analysis on Knowledge-Grounded Dialogue with Information Source Annotation. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop), pages 237–243, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- Is a Knowledge-based Response Engaging?: An Analysis on Knowledge-Grounded Dialogue with Information Source Annotation (Kodama et al., ACL 2023)
- PDF:
- https://preview.aclanthology.org/nodalida-main-page/2023.acl-srw.34.pdf