Abstract
This paper discusses the importance of uncovering uncertainty in end-to-end dialog tasks and presents our experimental results on uncertainty classification on the processed Ubuntu Dialog Corpus. We show that instead of retraining models for this specific purpose, we can capture the original retrieval model’s underlying confidence concerning the best prediction using trivial additional computation.- Anthology ID:
- 2020.acl-main.182
- Volume:
- Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
- Month:
- July
- Year:
- 2020
- Address:
- Online
- Editors:
- Dan Jurafsky, Joyce Chai, Natalie Schluter, Joel Tetreault
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 2013–2020
- Language:
- URL:
- https://aclanthology.org/2020.acl-main.182
- DOI:
- 10.18653/v1/2020.acl-main.182
- Cite (ACL):
- Yulan Feng, Shikib Mehri, Maxine Eskenazi, and Tiancheng Zhao. 2020. “None of the Above”: Measure Uncertainty in Dialog Response Retrieval. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 2013–2020, Online. Association for Computational Linguistics.
- Cite (Informal):
- “None of the Above”: Measure Uncertainty in Dialog Response Retrieval (Feng et al., ACL 2020)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-2/2020.acl-main.182.pdf