论文标题
提问重写可以帮助对话问题回答吗？
Can Question Rewriting Help Conversational Question Answering?
论文作者
论文摘要
问题重写（QR）是对话问题回答（CQA）的子任务（CQA），旨在通过以独立形式重新提出问题来缓解对话历史之间理解依赖性的挑战。尽管看似合理，但几乎没有证据证明QR是CQA缓解方法的合理性。为了验证QR在CQA中的有效性，我们研究了一种集成QR和CQA任务的增强学习方法，并且不需要针对目标CQA的相应QR数据集。但是，我们发现RL方法与端到端基线相当。我们提供了对失败的分析，并描述了为CQA开发QR的难度。
Question rewriting (QR) is a subtask of conversational question answering (CQA) aiming to ease the challenges of understanding dependencies among dialogue history by reformulating questions in a self-contained form. Despite seeming plausible, little evidence is available to justify QR as a mitigation method for CQA. To verify the effectiveness of QR in CQA, we investigate a reinforcement learning approach that integrates QR and CQA tasks and does not require corresponding QR datasets for targeted CQA. We find, however, that the RL method is on par with the end-to-end baseline. We provide an analysis of the failure and describe the difficulty of exploiting QR for CQA.
