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

ACL 2022  ·  Zhanming Jie, Jierui Li, Wei Lu ·

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.

PDF Abstract ACL 2022 PDF ACL 2022 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Math Word Problem Solving Math23K Roberta-DeductReasoner Accuracy (5-fold) 83 # 5
Math Word Problem Solving MathQA Roberta-DeductReasoner Answer Accuracy 78.6 # 4
Math Word Problem Solving MAWPS Roberta-DeductReasoner Accuracy (%) 92 # 7
Math Word Problem Solving SVAMP Roberta-DeductReasoner Execution Accuracy 47.3 # 14

Methods


No methods listed for this paper. Add relevant methods here