Question Directed Graph Attention Network for Numerical Reasoning over Text

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

arxiv: 2009.07448 · v2 · pith:F6WWXOTZnew · submitted 2020-09-16 · 💻 cs.AI

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

show 1 more author

Wei Chu

This is my paper

classification 💻 cs.AI

keywords graphreasoningnumericalquestionattentioncontextdirectednetwork

0 comments

read the original 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

This paper has not been read by Pith yet.

discussion (0)

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models
cs.AI 2024-08 conditional novelty 6.0

Empirical analysis shows scaling inference compute via strategies like tree search can be more efficient than scaling model parameters, with 7B models plus novel search outperforming 34B models.