To Answer or Not To Answer? Improving Machine Reading Comprehension Model with Span-based Contrastive Learning
Yunjie Ji, Liangyu Chen, Chenxiao Dou, Baochang Ma, Xiangang Li
Abstract
Machine Reading Comprehension with Unanswerable Questions is a difficult NLP task, challenged by the questions which can not be answered from passages.It is observed that subtle literal changes often make an answerable question unanswerable, however, most MRC models fail to recognize such changes.To address this problem, in this paper, we propose a span-based method of Contrastive Learning (spanCL) which explicitly contrast answerable questions with their answerable and unanswerable counterparts at the answer span level.With spanCL, MRC models are forced to perceive crucial semantic changes from slight literal differences.Experiments on SQuAD 2.0 dataset show that spanCL can improve baselines significantly, yielding 0.86~2.14 absolute EM improvements. Additional experiments also show that spanCL is an effective way to utilize generated questions.- Anthology ID:
- 2022.findings-naacl.96
- Volume:
- Findings of the Association for Computational Linguistics: NAACL 2022
- Month:
- July
- Year:
- 2022
- Address:
- Seattle, United States
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1292–1300
- Language:
- URL:
- https://aclanthology.org/2022.findings-naacl.96
- DOI:
- 10.18653/v1/2022.findings-naacl.96
- Cite (ACL):
- Yunjie Ji, Liangyu Chen, Chenxiao Dou, Baochang Ma, and Xiangang Li. 2022. To Answer or Not To Answer? Improving Machine Reading Comprehension Model with Span-based Contrastive Learning. In Findings of the Association for Computational Linguistics: NAACL 2022, pages 1292–1300, Seattle, United States. Association for Computational Linguistics.
- Cite (Informal):
- To Answer or Not To Answer? Improving Machine Reading Comprehension Model with Span-based Contrastive Learning (Ji et al., Findings 2022)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2022.findings-naacl.96.pdf
- Data
- SQuAD