Towards Tractable Mathematical Reasoning: Challenges, Strategies, and Opportunities for Solving Math Word Problems

Abstract

Mathematical reasoning would be one of the next frontiers for artificial intelligence to make significant progress. The ongoing surge to solve math word problems (MWPs) and hence achieve better mathematical reasoning ability would continue to be a key line of research in the coming time. We inspect non-neural and neural methods to solve math word problems narrated in a natural language. We also highlight the ability of these methods to be generalizable, mathematically reasonable, interpretable, and explainable. Neural approaches dominate the current state of the art, and we survey them highlighting three strategies to MWP solving: (1) direct answer generation, (2) expression tree generation for inferring answers, and (3) template retrieval for answer computation. Moreover, we discuss technological approaches, review the evolution of intuitive design choices to solve MWPs, and examine them for mathematical reasoning ability. We finally identify several gaps that warrant the need for external knowledge and knowledge-infused learning, among several other opportunities in solving MWPs.

15 pages, 2 tables, 4 figures

References in corpus (22)

• SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems
• Measuring Mathematical Problem Solving With the MATH Dataset
• K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters
• MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms
• WT5?! Training Text-to-Text Models to Explain their Predictions
• Analysing Mathematical Reasoning Abilities of Neural Models
• Robust Understanding of Word Problems with Extraneous Information
• Recent Advances in Natural Language Inference: A Survey of Benchmarks, Resources, and Approaches
• Deep Learning for Symbolic Mathematics
• Ape210K: A Large-Scale and Template-Rich Dataset of Math Word Problems
• Data-Driven Methods for Solving Algebra Word Problems
• On the Possibilities and Limitations of Multi-hop Reasoning Under Linguistic Imperfections
• KI-BERT: Infusing Knowledge Context for Better Language and Domain Understanding
• Reverse Operation based Data Augmentation for Solving Math Word Problems
• A framework for predicting, interpreting, and improving Learning Outcomes
• Solving Arithmetic Word Problems with Transformers and Preprocessing of Problem Text
• NumNet: Machine Reading Comprehension with Numerical Reasoning
• A Diverse Corpus for Evaluating and Developing English Math Word Problem Solvers
• SMART: A Situation Model for Algebra Story Problems via Attributed Grammar
• A Meaning-based Statistical English Math Word Problem Solver
• A Reinforcement Learning Environment for Mathematical Reasoning via Program Synthesis
• Neural-Symbolic Solver for Math Word Problems with Auxiliary Tasks