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.
@article{arxiv.2204.06239,
title = {Can Question Rewriting Help Conversational Question Answering?},
author = {Etsuko Ishii and Yan Xu and Samuel Cahyawijaya and Bryan Wilie},
journal= {arXiv preprint arXiv:2204.06239},
year = {2022}
}
Comments
Accepted at Workshop on Insights from Negative Results in NLP at ACL2022