Reinforced Question Rewriting for Conversational Question Answering
This work addresses the challenge of conversational question answering in industry settings by enabling the reuse of single-turn QA systems without training from scratch, though it is incremental as it builds on prior rewriting methods.
The paper tackles the problem of making conversational questions self-contained for use with existing single-turn QA systems by proposing a reinforcement learning approach that uses QA feedback to supervise the rewriting model, resulting in improved QA performance over baselines for both extractive and retrieval QA.
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.