AdaCQR: Enhancing Query Reformulation for Conversational Search via Sparse and Dense Retrieval Alignment
This work addresses the challenge of generalizing conversational search queries across different retrieval systems, offering incremental improvements in efficiency and robustness for information-seeking tasks.
The paper tackles the problem of conversational query reformulation by proposing AdaCQR, a framework that aligns reformulation models with both sparse and dense retrieval systems to improve generalization across diverse retrieval environments, achieving superior performance on TopiOCQA and QReCC datasets.
Conversational Query Reformulation (CQR) has significantly advanced in addressing the challenges of conversational search, particularly those stemming from the latent user intent and the need for historical context. Recent works aimed to boost the performance of CQR through alignment. However, they are designed for one specific retrieval system, which potentially results in sub-optimal generalization. To overcome this limitation, we present a novel framework AdaCQR. By aligning reformulation models with both term-based and semantic-based retrieval systems, AdaCQR enhances the generalizability of information-seeking queries among diverse retrieval environments through a two-stage training strategy. Moreover, two effective approaches are proposed to obtain superior labels and diverse input candidates, boosting the efficiency and robustness of the framework. Experimental results on the TopiOCQA and QReCC datasets demonstrate that AdaCQR outperforms the existing methods in a more efficient framework, offering both quantitative and qualitative improvements in conversational query reformulation.