DISK: Domain-constrained Instance Sketch for Math Word Problem Generation
Tianyang
Cao
author
Shuang
Zeng
author
Xiaodan
Xu
author
Mairgup
Mansur
author
Baobao
Chang
author
2022-10
text
Proceedings of the 29th International Conference on Computational Linguistics
International Committee on Computational Linguistics
Gyeongju, Republic of Korea
conference publication
A math word problem (MWP) is a coherent narrative which reflects the underlying logic of math equations. Successful MWP generation can automate the writing of mathematics questions. Previous methods mainly generate MWP text based on inflexible pre-defined templates. In this paper, we propose a neural model for generating MWP text from math equations. Firstly, we incorporate a matching model conditioned on the domain knowledge to retrieve a MWP instance which is most consistent with the ground-truth, where the domain is a latent variable extracted with a domain summarizer. Secondly, by constructing a Quantity Cell Graph (QCG) from the retrieved MWP instance and reasoning over it, we improve the model’s comprehension of real-world scenarios and derive a domain-constrained instance sketch to guide the generation. Besides, the QCG also interacts with the equation encoder to enhance the alignment between math tokens (e.g., quantities and variables) and MWP text. Experiments and empirical analysis on educational MWP set show that our model achieves impressive performance in both automatic evaluation metrics and human evaluation metrics.
cao-etal-2022-disk
https://aclanthology.org/2022.coling-1.551
2022-10
6327
6339