IterCQR: Iterative Conversational Query Reformulation with Retrieval Guidance

TL;DR

IterCQR introduces an iterative, reward-guided training approach for conversational query reformulation that eliminates the need for human-annotated rewrites, significantly improving retrieval performance across various datasets and settings.

Contribution

It presents a novel, reward-based training method for query reformulation that outperforms previous approaches relying on manual rewrites.

Findings

Achieves state-of-the-art results on multiple datasets

Effective in low-resource and unseen dataset scenarios

Improves retrieval performance with both sparse and dense retrievers

Abstract

Conversational search aims to retrieve passages containing essential information to answer queries in a multi-turn conversation. In conversational search, reformulating context-dependent conversational queries into stand-alone forms is imperative to effectively utilize off-the-shelf retrievers. Previous methodologies for conversational query reformulation frequently depend on human-annotated rewrites. However, these manually crafted queries often result in sub-optimal retrieval performance and require high collection costs. To address these challenges, we propose Iterative Conversational Query Reformulation (IterCQR), a methodology that conducts query reformulation without relying on human rewrites. IterCQR iteratively trains the conversational query reformulation (CQR) model by directly leveraging information retrieval (IR) signals as a reward. Our IterCQR training guides the CQR model such that generated queries contain necessary information from the previous dialogue context. Our proposed method shows state-of-the-art performance on two widely-used datasets, demonstrating its effectiveness on both sparse and dense retrievers. Moreover, IterCQR exhibits superior performance in challenging settings such as generalization on unseen datasets and low-resource scenarios.