A Surprisingly Simple yet Effective Multi-Query Rewriting Method for Conversational Passage Retrieval

TL;DR

This paper introduces a simple yet effective multi-query rewriting method for conversational passage retrieval that leverages beam search to generate multiple queries without extra cost, improving retrieval performance.

Contribution

It proposes a neural query rewriter that produces multiple queries via beam search and integrates them into retrieval, achieving state-of-the-art results efficiently.

Findings

Multi-query rewriting improves retrieval accuracy.

The method achieves state-of-the-art performance.

No additional computational cost due to beam search.

Abstract

Conversational passage retrieval is challenging as it often requires the resolution of references to previous utterances and needs to deal with the complexities of natural language, such as coreference and ellipsis. To address these challenges, pre-trained sequence-to-sequence neural query rewriters are commonly used to generate a single de-contextualized query based on conversation history. Previous research shows that combining multiple query rewrites for the same user utterance has a positive effect on retrieval performance. We propose the use of a neural query rewriter to generate multiple queries and show how to integrate those queries in the passage retrieval pipeline efficiently. The main strength of our approach lies in its simplicity: it leverages how the beam search algorithm works and can produce multiple query rewrites at no additional cost. Our contributions further include devising ways to utilize multi-query rewrites in both sparse and dense first-pass retrieval. We demonstrate that applying our approach on top of a standard passage retrieval pipeline delivers state-of-the-art performance without sacrificing efficiency.