A Multi-Type Multi-Span Network for Reading Comprehension that Requires Discrete Reasoning

Minghao Hu, Yuxing Peng, Zhen Huang, Dongsheng Li


Abstract
Rapid progress has been made in the field of reading comprehension and question answering, where several systems have achieved human parity in some simplified settings. However, the performance of these models degrades significantly when they are applied to more realistic scenarios, such as answers involve various types, multiple text strings are correct answers, or discrete reasoning abilities are required. In this paper, we introduce the Multi-Type Multi-Span Network (MTMSN), a neural reading comprehension model that combines a multi-type answer predictor designed to support various answer types (e.g., span, count, negation, and arithmetic expression) with a multi-span extraction method for dynamically producing one or multiple text spans. In addition, an arithmetic expression reranking mechanism is proposed to rank expression candidates for further confirming the prediction. Experiments show that our model achieves 79.9 F1 on the DROP hidden test set, creating new state-of-the-art results. Source code (https://github.com/huminghao16/MTMSN) is released to facilitate future work.
Anthology ID:
D19-1170
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Editors:
Kentaro Inui, Jing Jiang, Vincent Ng, Xiaojun Wan
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
1596–1606
Language:
URL:
https://aclanthology.org/D19-1170
DOI:
10.18653/v1/D19-1170
Bibkey:
Cite (ACL):
Minghao Hu, Yuxing Peng, Zhen Huang, and Dongsheng Li. 2019. A Multi-Type Multi-Span Network for Reading Comprehension that Requires Discrete Reasoning. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 1596–1606, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
A Multi-Type Multi-Span Network for Reading Comprehension that Requires Discrete Reasoning (Hu et al., EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/D19-1170.pdf
Attachment:
 D19-1170.Attachment.zip
Code
 huminghao16/MTMSN
Data
DROPSQuAD