Learning to Ask Unanswerable Questions for Machine Reading Comprehension

Haichao Zhu, Li Dong, Furu Wei, Wenhui Wang, Bing Qin, Ting Liu


Abstract
Machine reading comprehension with unanswerable questions is a challenging task. In this work, we propose a data augmentation technique by automatically generating relevant unanswerable questions according to an answerable question paired with its corresponding paragraph that contains the answer. We introduce a pair-to-sequence model for unanswerable question generation, which effectively captures the interactions between the question and the paragraph. We also present a way to construct training data for our question generation models by leveraging the existing reading comprehension dataset. Experimental results show that the pair-to-sequence model performs consistently better compared with the sequence-to-sequence baseline. We further use the automatically generated unanswerable questions as a means of data augmentation on the SQuAD 2.0 dataset, yielding 1.9 absolute F1 improvement with BERT-base model and 1.7 absolute F1 improvement with BERT-large model.
Anthology ID:
P19-1415
Volume:
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2019
Address:
Florence, Italy
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4238–4248
Language:
URL:
https://aclanthology.org/P19-1415
DOI:
10.18653/v1/P19-1415
Bibkey:
Cite (ACL):
Haichao Zhu, Li Dong, Furu Wei, Wenhui Wang, Bing Qin, and Ting Liu. 2019. Learning to Ask Unanswerable Questions for Machine Reading Comprehension. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 4238–4248, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
Learning to Ask Unanswerable Questions for Machine Reading Comprehension (Zhu et al., ACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/P19-1415.pdf
Video:
 https://vimeo.com/385197035
Data
SQuAD