NumNet: Machine Reading Comprehension with Numerical Reasoning

Qiu Ran, Yankai Lin, Peng Li, Jie Zhou, Zhiyuan Liu


Abstract
Numerical reasoning, such as addition, subtraction, sorting and counting is a critical skill in human’s reading comprehension, which has not been well considered in existing machine reading comprehension (MRC) systems. To address this issue, we propose a numerical MRC model named as NumNet, which utilizes a numerically-aware graph neural network to consider the comparing information and performs numerical reasoning over numbers in the question and passage. Our system achieves an EM-score of 64.56% on the DROP dataset, outperforming all existing machine reading comprehension models by considering the numerical relations among numbers.
Anthology ID:
D19-1251
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
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
2474–2484
Language:
URL:
https://aclanthology.org/D19-1251
DOI:
10.18653/v1/D19-1251
Bibkey:
Cite (ACL):
Qiu Ran, Yankai Lin, Peng Li, Jie Zhou, and Zhiyuan Liu. 2019. NumNet: Machine Reading Comprehension with Numerical 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 2474–2484, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
NumNet: Machine Reading Comprehension with Numerical Reasoning (Ran et al., EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/D19-1251.pdf
Attachment:
 D19-1251.Attachment.pdf
Code
 ranqiu92/NumNet +  additional community code
Data
DROPRACESQuAD