TL;DR
This paper evaluates various question rewriting methods for conversational passage retrieval on TREC CAsT datasets, demonstrating that combining different methods yields state-of-the-art results in a unified retrieval pipeline.
Contribution
It provides a comprehensive comparison of question rewriting techniques under the same retrieval setup and shows that combining methods improves retrieval performance.
Findings
Combining different question rewriting methods enhances retrieval accuracy.
State-of-the-art performance achieved on TREC CAsT 2019 and 2020 datasets.
Thorough evaluation under a unified pipeline clarifies the effectiveness of various methods.
Abstract
Conversational passage retrieval relies on question rewriting to modify the original question so that it no longer depends on the conversation history. Several methods for question rewriting have recently been proposed, but they were compared under different retrieval pipelines. We bridge this gap by thoroughly evaluating those question rewriting methods on the TREC CAsT 2019 and 2020 datasets under the same retrieval pipeline. We analyze the effect of different types of question rewriting methods on retrieval performance and show that by combining question rewriting methods of different types we can achieve state-of-the-art performance on both datasets.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
