Learning Fine-Grained Expressions to Solve Math Word Problems
Danqing
Huang
author
Shuming
Shi
author
Chin-Yew
Lin
author
Jian
Yin
author
2017-09
text
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
Association for Computational Linguistics
Copenhagen, Denmark
conference publication
This paper presents a novel template-based method to solve math word problems. This method learns the mappings between math concept phrases in math word problems and their math expressions from training data. For each equation template, we automatically construct a rich template sketch by aggregating information from various problems with the same template. Our approach is implemented in a two-stage system. It first retrieves a few relevant equation system templates and aligns numbers in math word problems to those templates for candidate equation generation. It then does a fine-grained inference to obtain the final answer. Experiment results show that our method achieves an accuracy of 28.4% on the linear Dolphin18K benchmark, which is 10% (54% relative) higher than previous state-of-the-art systems while achieving an accuracy increase of 12% (59% relative) on the TS6 benchmark subset.
huang-etal-2017-learning
10.18653/v1/D17-1084
https://aclanthology.org/D17-1084
2017-09
805
814