DeepAI AI Chat
Log In Sign Up

Translating a Math Word Problem to an Expression Tree

by   Lei Wang, et al.
University of Electronic Science and Technology of China

Sequence-to-sequence (SEQ2SEQ) models have been successfully applied to automatic math word problem solving. Despite its simplicity, a drawback still remains: a math word problem can be correctly solved by more than one equations. This non-deterministic transduction harms the performance of maximum likelihood estimation. In this paper, by considering the uniqueness of expression tree, we propose an equation normalization method to normalize the duplicated equations. Moreover, we analyze the performance of three popular SEQ2SEQ models on the math word problem solving. We find that each model has its own specialty in solving problems, consequently an ensemble model is then proposed to combine their advantages. Experiments on dataset Math23K show that the ensemble model with equation normalization significantly outperforms the previous state-of-the-art methods.


page 1

page 2

page 3

page 4


Solving Math Word Problems by Scoring Equations with Recursive Neural Networks

Solving math word problems is a cornerstone task in assessing language u...

Seeking Diverse Reasoning Logic: Controlled Equation Expression Generation for Solving Math Word Problems

To solve Math Word Problems, human students leverage diverse reasoning l...

On Solving Word Equations via Program Transformation

The paper presents an experiment of solving word equations via specializ...

Ape210K: A Large-Scale and Template-Rich Dataset of Math Word Problems

Automatic math word problem solving has attracted growing attention in r...

Data-Driven Methods for Solving Algebra Word Problems

We explore contemporary, data-driven techniques for solving math word pr...

Semantically-Aligned Universal Tree-Structured Solver for Math Word Problems

A practical automatic textual math word problems (MWPs) solver should be...

Program Specialization as a Tool for Solving Word Equations

The paper focuses on the automatic generating of the witnesses for the w...