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. |
Year | DOI | Venue |
---|---|---|
2019 | 10.18653/v1/D19-1251 | EMNLP/IJCNLP (1) |
DocType | Volume | Citations |
Conference | D19-1 | 1 |
PageRank | References | Authors |
0.38 | 0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Qiu Ran | 1 | 2 | 1.41 |
Yankai Lin | 2 | 607 | 28.37 |
Peng Li | 3 | 146 | 21.34 |
Jie Zhou | 4 | 13 | 11.09 |
Zhiyuan Liu | 5 | 2037 | 123.68 |