Neural Mathematical Solver with Enhanced Formula Structure
By Zhenya Huang, Qi Liu, Weibo Gao, Jinze Wu, Yu Yin, Hongya Wang, Enhong Chen. 2020
29 citations recorded by the source corpus.
Automatically answering mathematical problems is a challenging task since it requires not only the ability of linguistic understanding but also mathematical comprehension. Existing studies usually explore solutions on the elementary math word problems that aim to understand the questions described in natural language narratives, which are not capable of solving more general problems containing structural formulas. To this end, in this paper, we propose a novel Neural Mathematical Solver (NMS) with enhanced formula structures. Specifically, we first frame the formulas in a certain problem as a TeX dependency graph to preserve formula-enriched structures. Then, we design a formula graph network (FGN) to capture its mathematical relations. Next, we develop a novel architecture with two GRU models, connecting tokens from both word space and formula space together, to learn the linguistic semantics for the answers. Extensive experiments on a large-scale dataset demonstrate that NMS not only achieves better answer prediction but also visualizes reasonable mathematical representations of problems.
Subfields: Artificial Intelligence, Computational Theory and Mathematics
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
In Computational Theory and Mathematics
Citations in the corpus
- HMS: A Hierarchical Solver with Dependency-Enhanced Understanding for Math Word Problem (2021, background): “In recent years, more difficult mathematical problems were also tack-led (Huang et al. 2020) in addition to traditional MWP.”