A Meaning-Based Statistical English Math Word Problem Solver

By Chao-Chun Liang, Yu-Shiang Wong, Yi-Chung Lin, Keh-Yih Su. 2018

26 citations recorded by the source corpus.

We introduce MeSys, a meaning-based approach, for solving English math word problems (MWPs) via understanding and reasoning in this paper. It first analyzes the text, transforms both body and question parts into their corresponding logic forms, and then performs inference on them. The associated context of each quantity is represented with proposed role-tags (e.g., nsubj, verb, etc.), which provides the flexibility for annotating an extracted math quantity with its associated context information (i.e., the physical meaning of this quantity). Statistical models are proposed to select the operator and operands. A noisy dataset is designed to assess if a solver solves MWPs mainly via understanding or mechanical pattern matching. Experimental results show that our approach outperforms existing systems on both benchmark datasets and the noisy dataset, which demonstrates that the proposed approach understands the meaning of each quantity in the text more.

Subfields: Artificial Intelligence, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

Citations in the corpus

MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms (2019, background): “While this area is relatively unexplored, a prior approach to increasing robustness and interpretability of math word problem-solving models looks at using an adversarial dataset to determine if models are learning logical reasoning or exploiting dataset biases through pattern-matching (Liang et al.”
Learning to Reason Deductively: Math Word Problem Solving as Complex Relation Extraction (2022, methodology): “Traditional methods (Liang et al., 2018) applied rule-based approaches to extract the mathematical relations.”
A Diverse Corpus for Evaluating and Developing English Math Word Problem Solvers (2020, background): “the same problem type share a similar pattern (in language usages, logic representation, or inferences), they thus indicate stereotypical math operation patterns that could be adopted to solve an MWP (Liang et al., 2018).”
Neural-Symbolic Solver for Math Word Problems with Auxiliary Tasks (2021, background): “Liang et al. (2017b, 2018b) Chickens: 11, Rabbits: 15 equation tree Figure 1: An overview of our NS-Solver.”
Text2Math: End-to-end Parsing Text into Math Expressions (2019, methodology): “System AI2 IL Average ∗Liang et al. (2018) (Statistical) 81.”