A Comparison of Question Rewriting Methods for Conversational Passage Retrieval
This work addresses the problem of inconsistent evaluation in conversational retrieval for researchers, though it is incremental as it builds on existing methods.
The study compared various question rewriting methods for conversational passage retrieval using the TREC CAsT 2019 and 2020 datasets under a unified pipeline, finding that combining different types of methods achieved state-of-the-art performance.
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.