%0 Conference Proceedings %T Learning to Ask Unanswerable Questions for Machine Reading Comprehension %A Zhu, Haichao %A Dong, Li %A Wei, Furu %A Wang, Wenhui %A Qin, Bing %A Liu, Ting %Y Korhonen, Anna %Y Traum, David %Y Màrquez, Lluís %S Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics %D 2019 %8 July %I Association for Computational Linguistics %C Florence, Italy %F zhu-etal-2019-learning %X 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. %R 10.18653/v1/P19-1415 %U https://aclanthology.org/P19-1415 %U https://doi.org/10.18653/v1/P19-1415 %P 4238-4248