Multi-task Learning with Sample Re-weighting for Machine Reading Comprehension
Yichong Xu, Xiaodong Liu, Yelong Shen, Jingjing Liu, Jianfeng Gao
Abstract
We propose a multi-task learning framework to learn a joint Machine Reading Comprehension (MRC) model that can be applied to a wide range of MRC tasks in different domains. Inspired by recent ideas of data selection in machine translation, we develop a novel sample re-weighting scheme to assign sample-specific weights to the loss. Empirical study shows that our approach can be applied to many existing MRC models. Combined with contextual representations from pre-trained language models (such as ELMo), we achieve new state-of-the-art results on a set of MRC benchmark datasets. We release our code at https://github.com/xycforgithub/MultiTask-MRC.- Anthology ID:
- N19-1271
- Volume:
- Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
- Month:
- June
- Year:
- 2019
- Address:
- Minneapolis, Minnesota
- Editors:
- Jill Burstein, Christy Doran, Thamar Solorio
- Venue:
- NAACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 2644–2655
- Language:
- URL:
- https://aclanthology.org/N19-1271
- DOI:
- 10.18653/v1/N19-1271
- Cite (ACL):
- Yichong Xu, Xiaodong Liu, Yelong Shen, Jingjing Liu, and Jianfeng Gao. 2019. Multi-task Learning with Sample Re-weighting for Machine Reading Comprehension. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 2644–2655, Minneapolis, Minnesota. Association for Computational Linguistics.
- Cite (Informal):
- Multi-task Learning with Sample Re-weighting for Machine Reading Comprehension (Xu et al., NAACL 2019)
- PDF:
- https://preview.aclanthology.org/autopr/N19-1271.pdf
- Code
- xycforgithub/MultiTask-MRC + additional community code
- Data
- MS MARCO, NewsQA, SQuAD