AdaCQR: Enhancing Query Reformulation for Conversational Search via Sparse and Dense Retrieval Alignment

TL;DR

AdaCQR is a novel framework that improves conversational query reformulation by aligning models with both term-based and semantic retrieval systems, enhancing generalization across diverse environments.

Contribution

It introduces a two-stage training strategy and new approaches for labels and input candidates to boost robustness and efficiency in query reformulation.

Findings

Outperforms existing methods on TopiOCQA and QReCC datasets.

Provides quantitative and qualitative improvements in reformulation.

Enhances generalizability across different retrieval systems.

Abstract

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.