History-Aware Conversational Dense Retrieval

Fengran Mo, Chen Qu, Kelong Mao, Tianyu Zhu, Zhan Su, Kaiyu Huang, Jian-Yun Nie


Abstract
Conversational search facilitates complex information retrieval by enabling multi-turn interactions between users and the system. Supporting such interactions requires a comprehensive understanding of the conversational inputs to formulate a good search query based on historical information. In particular, the search query should include the relevant information from the previous conversation turns.However, current approaches for conversational dense retrieval primarily rely on fine-tuning a pre-trained ad-hoc retriever using the whole conversational search session, which can be lengthy and noisy. Moreover, existing approaches are limited by the amount of manual supervision signals in the existing datasets.To address the aforementioned issues, we propose a **H**istory-**A**ware **Conv**ersational **D**ense **R**etrieval (HAConvDR) system, which incorporates two ideas: context-denoised query reformulation and automatic mining of supervision signals based on the actual impact of historical turns.Experiments on two public conversational search datasets demonstrate the improved history modeling capability of HAConvDR, in particular for long conversations with topic shifts.
Anthology ID:
2024.findings-acl.792
Volume:
Findings of the Association for Computational Linguistics: ACL 2024
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
13366–13378
Language:
URL:
https://aclanthology.org/2024.findings-acl.792
DOI:
10.18653/v1/2024.findings-acl.792
Bibkey:
Cite (ACL):
Fengran Mo, Chen Qu, Kelong Mao, Tianyu Zhu, Zhan Su, Kaiyu Huang, and Jian-Yun Nie. 2024. History-Aware Conversational Dense Retrieval. In Findings of the Association for Computational Linguistics: ACL 2024, pages 13366–13378, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
History-Aware Conversational Dense Retrieval (Mo et al., Findings 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/autopr/2024.findings-acl.792.pdf