Learning to Reason Deductively: Math Word Problem Solving as Complex Relation Extraction

By Zhanming Jie, Jierui Li, Wei Dang Lu. 2022

93 citations recorded by the source corpus.

Solving math word problems requires deductive reasoning over the quantities in the text. Various recent research efforts mostly relied on sequence-to-sequence or sequence-to-tree models to generate mathematical expressions without explicitly performing relational reasoning between quantities in the given context. While empirically effective, such approaches typically do not provide explanations for the generated expressions. In this work, we view the task as a complex relation extraction problem, proposing a novel approach that presents explainable deductive reasoning steps to iteratively construct target expressions, where each step involves a primitive operation over two quantities defining their relation. Through extensive experiments on four benchmark datasets, we show that the proposed model significantly outperforms existing strong baselines. We further demonstrate that the deductive procedure not only presents more explainable steps but also enables us to make more accurate predictions on questions that require more complex reasoning.

Subfields: 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 Natural Language Processing

Citations in the corpus

A Survey of Deep Learning for Mathematical Reasoning (2022, unknown): “For example, MWP-BERT (Liang et al., 2022b) uses a backbone of BERT (110M) (Devlin et al., 2019) and RoBERTa (123M) (Liu et al., 2019b) for Math Word Problems.”
Scaling Relationship on Learning Mathematical Reasoning with Large Language Models (2023, methodology): “…on the reasoning tasks of math word problems (MWP), and methods are evaluated on the benchmarks spanning different levels of MWPs (Koncel-Kedziorski et al. (2016); Patel et al. (2021); Lan et al. (2021); Cobbe et al. (2021); Jie et al. (2022); Yuan et al. (2023a); Fu et al. (2023a), inter alia).”