ICR: Iterative Clarification and Rewriting for Conversational Search
This addresses a bottleneck in conversational search for users by improving retrieval accuracy, though it is incremental as it builds on existing rewriting paradigms.
The paper tackles the problem of multiple fuzzy expressions in conversational query rewriting by proposing ICR, an iterative framework that alternates between generating clarification questions and rewritten queries, achieving state-of-the-art performance on two popular datasets.
Most previous work on Conversational Query Rewriting employs an end-to-end rewriting paradigm. However, this approach is hindered by the issue of multiple fuzzy expressions within the query, which complicates the simultaneous identification and rewriting of multiple positions. To address this issue, we propose a novel framework ICR (Iterative Clarification and Rewriting), an iterative rewriting scheme that pivots on clarification questions. Within this framework, the model alternates between generating clarification questions and rewritten queries. The experimental results show that our ICR can continuously improve retrieval performance in the clarification-rewriting iterative process, thereby achieving state-of-the-art performance on two popular datasets.