CONQRR: Conversational Query Rewriting for Retrieval with Reinforcement Learning
Preprint
Abstract
Compared to standard retrieval tasks, passage retrieval for conversational question answering (CQA) poses new challenges in understanding the current user question, as each question needs to be interpreted within the dialogue context. Moreover, it can be expensive to re-train well-established retrievers such as search engines that are originally developed for non-conversational queries. To facilitate their use, we develop a query rewriting model CONQRR that rewrites a conversational question in the context into a standalone question. It is trained with a novel reward function to directly optimize towards retrieval using reinforcement learning and can be adapted to any off-the-shelf retriever. We show that CONQRR achieves state-of-the-art results on a recent open-domain CQA dataset containing conversations from three different sources, and is effective for two different off-the-shelf retrievers. Our extensive analysis also shows the robustness of CONQRR to out-of-domain dialogues as well as to zero query rewriting supervision.Keywords
All Related Versions
This publication has 25 references indexed in Scilit:
- Few-Shot Conversational Dense Retrieval2021
- Question Rewriting for Conversational Question Answering2021
- Open-Retrieval Conversational Question Answering2020
- Few-Shot Generative Conversational Query Rewriting2020
- CAsT-19: A Dataset for Conversational Information Seeking2020
- CoQA: A Conversational Question Answering ChallengeTransactions of the Association for Computational Linguistics, 2019
- Anserini2017
- Self-Critical Sequence Training for Image Captioning2017
- Conversation in information-seeking contexts: A test of an analytical frameworkLibrary & Information Science Research, 1997
- Cases, Scripts, and Information-Seeking Strategies: On the Design of Interactive Information Retrieval SystemsExpert Systems with Applications, 1995