Papers › NumNet: Machine Reading Comprehension with Numerical Reasoning

NumNet: Machine Reading Comprehension with Numerical Reasoning

15 Oct 2019IJCNLP 2019 11arXiv:1910.06701archive 2025-07-28

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.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

ranqiu92/NumNet officialmentioned in paperpytorch report
wenhuchen/gnn-tabfact mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Graph Neural NetworkMachine Reading ComprehensionQuestion AnsweringReading Comprehension

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Question Answering DROP Test NumNet F1 67.97 #10 of 16 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Graph Neural Network

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections