Neural Mathematical Solver with Enhanced Formula Structure
Lists
Only you see this
Abstract
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.
BibTeX
@inproceedings{huang2020neural,
author = {Zhenya Huang and Qi Liu and Weibo Gao and Jinze Wu and Yu Yin and Hao Wang and Enhong Chen},
title = {{Neural Mathematical Solver with Enhanced Formula Structure}},
booktitle = {International ACM SIGIR Conference on Research and Development in Information Retrieval},
year = {2020},
doi = {10.1145/3397271.3401227},
}Loading related content...