Few-Shot Generative Conversational Query Rewriting
This work addresses the problem of improving information retrieval for conversational queries, offering a practical solution with significant gains, though it is incremental as it builds on existing generative models and weak supervision techniques.
The paper tackles conversational query rewriting by developing a few-shot generative approach using GPT-2 fine-tuned with weak supervision from ad hoc search sessions, resulting in a 12% improvement in state-of-the-art ranking accuracy on the TREC Conversational Assistance Track with limited manual data.
Conversational query rewriting aims to reformulate a concise conversational query to a fully specified, context-independent query that can be effectively handled by existing information retrieval systems. This paper presents a few-shot generative approach to conversational query rewriting. We develop two methods, based on rules and self-supervised learning, to generate weak supervision data using large amounts of ad hoc search sessions, and to fine-tune GPT-2 to rewrite conversational queries. On the TREC Conversational Assistance Track, our weakly supervised GPT-2 rewriter improves the state-of-the-art ranking accuracy by 12%, only using very limited amounts of manual query rewrites. In the zero-shot learning setting, the rewriter still gives a comparable result to previous state-of-the-art systems. Our analyses reveal that GPT-2 effectively picks up the task syntax and learns to capture context dependencies, even for hard cases that involve group references and long-turn dependencies.