Data-Driven Methods for Solving Algebra Word Problems

Abstract

We explore contemporary, data-driven techniques for solving math word problems over recent large-scale datasets. We show that well-tuned neural equation classifiers can outperform more sophisticated models such as sequence to sequence and self-attention across these datasets. Our error analysis indicates that, while fully data driven models show some promise, semantic and world knowledge is necessary for further advances.

References in corpus (3)

• Sequence to Sequence Learning with Neural Networks
• A Structured Self-attentive Sentence Embedding
• Stochastic Answer Networks for Machine Reading Comprehension

Cited by in corpus (8)

• Graph-to-Tree Neural Networks for Learning Structured Input-Output Translation with Applications to Semantic Parsing and Math Word Problem
• The Gap of Semantic Parsing: A Survey on Automatic Math Word Problem Solvers
• Semantically-Aligned Equation Generation for Solving and Reasoning Math Word Problems
• Reverse Operation based Data Augmentation for Solving Math Word Problems
• Solving Arithmetic Word Problems with Transformers and Preprocessing of Problem Text
• Learning by Fixing: Solving Math Word Problems with Weak Supervision
• Towards Tractable Mathematical Reasoning: Challenges, Strategies, and Opportunities for Solving Math Word Problems
• Solving Arithmetic Word Problems Automatically Using Transformer and Unambiguous Representations