Abstract
Many natural language questions require qualitative, quantitative or logical comparisons between two entities or events. This paper addresses the problem of improving the accuracy and consistency of responses to comparison questions by integrating logic rules and neural models. Our method leverages logical and linguistic knowledge to augment labeled training data and then uses a consistency-based regularizer to train the model. Improving the global consistency of predictions, our approach achieves large improvements over previous methods in a variety of question answering (QA) tasks, including multiple-choice qualitative reasoning, cause-effect reasoning, and extractive machine reading comprehension. In particular, our method significantly improves the performance of RoBERTa-based models by 1-5% across datasets. We advance state of the art by around 5-8% on WIQA and QuaRel and reduce consistency violations by 58% on HotpotQA. We further demonstrate that our approach can learn effectively from limited data.- Anthology ID:
- 2020.acl-main.499
- Volume:
- Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
- Month:
- July
- Year:
- 2020
- Address:
- Online
- Editors:
- Dan Jurafsky, Joyce Chai, Natalie Schluter, Joel Tetreault
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 5642–5650
- Language:
- URL:
- https://aclanthology.org/2020.acl-main.499
- DOI:
- 10.18653/v1/2020.acl-main.499
- Cite (ACL):
- Akari Asai and Hannaneh Hajishirzi. 2020. Logic-Guided Data Augmentation and Regularization for Consistent Question Answering. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 5642–5650, Online. Association for Computational Linguistics.
- Cite (Informal):
- Logic-Guided Data Augmentation and Regularization for Consistent Question Answering (Asai & Hajishirzi, ACL 2020)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-2/2020.acl-main.499.pdf
- Code
- AkariAsai/logic_guided_qa
- Data
- HotpotQA, QuaRel, WIQA