.png){kind=icon}
返回
Number-enhanced representation with hierarchical recursive tree decoding for math word problem solving
.png){kind=icon}
PRE
AI
DOI：10.1016/j.ipm.2023.103585.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Automatic solving math word problems (MWPs) is a number-intensive application in natural language processing (NLP). However, these existing methods are far from achieving acceptable levels of numeracy learning. As a result, the performance of these models is limited for mathe-matical reasoning. In addition, the mainstream tree decoder suffers from early-stage information loss, resulting in an unsatisfactory performance for complex problems with more operators. In this paper, we propose NERHRT (Number-Enhanced Representation with Hierarchical Recursive Tree Decoding), a simple yet effective number embedding method that produces the numerical reasoning via the decimal notation-based embedding and a dual-direction graph attention network. In addition, a hierarchical recursive tree-structured decoder is introduced to aggregate information from all ancestor nodes. Experiments show that our approach obtains the best performance on four popular benchmark datasets, and beats the state-of-the-art models with a large margin.
Keyword:
Math word problem solving
Numerical reasoning
Tree decoder
期刊
I
IF:
6.9
论文数:
5.2K
被引数:
1.4W
机构
引用论文
.png){kind=icon}
Phase Equilibria of Semiclathrate Hydrates of CO2, N2, CH4, or H2+ Tetra-n-butylammonium Bromide Aqueous SolutionPhase Equilibria of Semiclathrate Hydrates of CO2, N2, CH4,或H2 四-n-丁基溴化铵水溶液
PREAI
分享收藏 没有更多内容
没有更多内容