NumNet: Machine Reading Comprehension with Numerical Reasoning
This addresses the challenge of numerical reasoning in reading comprehension for AI systems, representing a strong specific gain in this domain.
The paper tackled the problem of numerical reasoning in machine reading comprehension by proposing NumNet, a model that uses a numerically-aware graph neural network to handle numerical relations, achieving an EM-score of 64.56% on the DROP dataset.
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.