Question Directed Graph Attention Network for Numerical Reasoning over Text
2020-09-16EMNLP 2020Code Available0· sign in to hype
Kunlong Chen, Weidi Xu, Xingyi Cheng, Zou Xiaochuan, Yuyu Zhang, Le Song, Taifeng Wang, Yuan Qi, Wei Chu
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/emnlp2020qdgat/qdgatOfficialIn paper★ 2
Abstract
Numerical reasoning over texts, such as addition, subtraction, sorting and counting, is a challenging machine reading comprehension task, since it requires both natural language understanding and arithmetic computation. To address this challenge, we propose a heterogeneous graph representation for the context of the passage and question needed for such reasoning, and design a question directed graph attention network to drive multi-step numerical reasoning over this context graph. The code link is at: https://github.com/emnlp2020qdgat/QDGAT
Tasks
Benchmark Results
| Dataset | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| DROP Test | QDGAT (ensemble) | F1 | 88.38 | — | Unverified |