通过迭代提问与重写，提升对话式搜索的查询准确性。
ICR: Iterative Clarification and Rewriting for Conversational Search
- 采用问答交替的迭代机制，逐步澄清模糊查询
- 在两个主流数据集上实现最优检索性能
- 适合需要高精度对话搜索的场景
以往对话式查询重写的多数工作采用端到端重写范式，但受限于查询中多重模糊表达，难以同时识别并重写多个位置。为此，我们提出一种新框架ICR（Iterative Clarification and Rewriting），基于澄清问题的迭代重写方案。模型在生成澄清问题和重写查询之间交替进行。实验结果表明，ICR能在澄清-重写迭代过程中持续提升检索性能，在两个流行数据集上达到当前最优水平。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。