Improving Compositional Generalization in Math Word Problem Solving

作     者：Lan, Yunshi Wang, Lei Jiang, Jing Lim, Ee-Peng 

作者机构：School of Data Science and Engineering East China Normal University China School of Computing and Information System Singapore Management University Singapore 

出 版 物：《arXiv》 (arXiv)

年 卷 期：2022年

核心收录：

主　　题：Iterative methods 

摘      要：Compositional generalization refers to a model s capability to generalize to newly composed input data based on the data components observed during training. It has triggered a series of compositional generalization analysis on different tasks as generalization is an important aspect of language and problem solving skills. However, the similar discussion on math word problems (MWPs) is limited. In this manuscript, we study compositional generalization in MWP solving. Specifically, we first introduce a data splitting method to create compositional splits from existing MWP datasets. Meanwhile, we synthesize data to isolate the effect of compositions. To improve the compositional generalization in MWP solving, we propose an iterative data augmentation method that includes diverse compositional variation into training data and could collaborate with MWP methods. During the evaluation, we examine a set of methods and find all of them encounter severe performance loss on the evaluated datasets. We also find our data augmentation method could significantly improve the compositional generalization of general MWP methods. Code is available at https://***/demoleiwang/CGMWP. © 2022, CC BY.