%0 Conference Proceedings
%T NumNet: Machine Reading Comprehension with Numerical Reasoning
%A Ran, Qiu
%A Lin, Yankai
%A Li, Peng
%A Zhou, Jie
%A Liu, Zhiyuan
%Y Inui, Kentaro
%Y Jiang, Jing
%Y Ng, Vincent
%Y Wan, Xiaojun
%S Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F ran-etal-2019-numnet
%X 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.
%R 10.18653/v1/D19-1251
%U https://aclanthology.org/D19-1251
%U https://doi.org/10.18653/v1/D19-1251
%P 2474-2484