Can Question Rewriting Help Conversational Question Answering?
This work addresses the problem of improving conversational question answering for AI systems, but it is incremental as it shows limited effectiveness of QR.
The study investigated whether question rewriting (QR) helps conversational question answering (CQA) by using a reinforcement learning approach that integrates QR and CQA without requiring QR datasets, but found it performed similarly to an end-to-end baseline.
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.