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.
@article{arxiv.1910.06701,
title = {NumNet: Machine Reading Comprehension with Numerical Reasoning},
author = {Qiu Ran and Yankai Lin and Peng Li and Jie Zhou and Zhiyuan Liu},
journal= {arXiv preprint arXiv:1910.06701},
year = {2019}
}
Comments
Accepted to EMNLP2019; 11 pages, 2 figures, 6 tables