Abstract
We deal with the scenario of conversational search, where user queries are under-specified or ambiguous. This calls for a mixed-initiative setup. User-asks (queries) and system-answers, as well as system-asks (clarification questions) and user response, in order to clarify her information needs. We focus on the task of selecting the next clarification question, given conversation context. Our method leverages passage retrieval from background content to fine-tune two deep-learning models for ranking candidate clarification questions. We evaluated our method on two different use-cases. The first is an open domain conversational search in a large web collection. The second is a task-oriented customer-support setup. We show that our method performs well on both use-cases.- Anthology ID:
- 2022.dialdoc-1.7
- Volume:
- Proceedings of the Second DialDoc Workshop on Document-grounded Dialogue and Conversational Question Answering
- Month:
- May
- Year:
- 2022
- Address:
- Dublin, Ireland
- Editors:
- Song Feng, Hui Wan, Caixia Yuan, Han Yu
- Venue:
- dialdoc
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 65–71
- Language:
- URL:
- https://aclanthology.org/2022.dialdoc-1.7
- DOI:
- 10.18653/v1/2022.dialdoc-1.7
- Cite (ACL):
- Yosi Mass, Doron Cohen, Asaf Yehudai, and David Konopnicki. 2022. Conversational Search with Mixed-Initiative - Asking Good Clarification Questions backed-up by Passage Retrieval. In Proceedings of the Second DialDoc Workshop on Document-grounded Dialogue and Conversational Question Answering, pages 65–71, Dublin, Ireland. Association for Computational Linguistics.
- Cite (Informal):
- Conversational Search with Mixed-Initiative - Asking Good Clarification Questions backed-up by Passage Retrieval (Mass et al., dialdoc 2022)
- PDF:
- https://preview.aclanthology.org/proper-vol2-ingestion/2022.dialdoc-1.7.pdf