NumNet: Machine Reading Comprehension with Numerical Reasoning

IJCNLP 2019  ·  Qiu Ran, Yankai Lin, Peng Li, Jie zhou, Zhiyuan Liu ·

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.

PDF Abstract IJCNLP 2019 PDF IJCNLP 2019 Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Question Answering DROP Test NumNet F1 67.97 # 10

Methods