Question Directed Graph Attention Network for Numerical Reasoning over Text

Kunlong Chen, Weidi Xu, Xingyi Cheng, Zou Xiaochuan, Yuyu Zhang, Le Song, Taifeng Wang, Yuan Qi, Wei Chu


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. Our model, which combines deep learning and graph reasoning, achieves remarkable results in benchmark datasets such as DROP.
Anthology ID:
2020.emnlp-main.549
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6759–6768
Language:
URL:
https://www.aclweb.org/anthology/2020.emnlp-main.549
DOI:
10.18653/v1/2020.emnlp-main.549
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/2020.emnlp-main.549.pdf