Conversational Question Answering (CQA) aims to answer questions contained within dialogues, which are not easily interpretable without context. Developing a model to rewrite conversational questions into self-contained ones is an emerging solution in industry settings as it allows using existing single-turn QA systems to avoid training a CQA model from scratch. Previous work trains rewriting models using human rewrites as supervision. However, such objectives are disconnected with QA models and therefore more human-like rewrites do not guarantee better QA performance. In this paper we propose using QA feedback to supervise the rewriting model with reinforcement learning. Experiments show that our approach can effectively improve QA performance over baselines for both extractive and retrieval QA. Furthermore, human evaluation shows that our method can generate more accurate and detailed rewrites when compared to human annotations.
@article{arxiv.2210.15777,
title = {Reinforced Question Rewriting for Conversational Question Answering},
author = {Zhiyu Chen and Jie Zhao and Anjie Fang and Besnik Fetahu and Oleg Rokhlenko and Shervin Malmasi},
journal= {arXiv preprint arXiv:2210.15777},
year = {2022}
}
Comments
A cleaned version of our paper Accepted by EMNLP 2022 (Industry Track)