Solving symbolic reasoning problems that require compositionality and systematicity is considered one of the key ingredients of human intelligence. However, symbolic reasoning is still a great challenge for deep learning models, which often cannot generalize the reasoning pattern to out-of-distribution test cases. In this work, we propose a hybrid system capable of solving arithmetic problems that require compositional and systematic reasoning over sequences of symbols. The model acquires such a skill by learning appropriate substitution rules, which are applied iteratively to the input string until the expression is completely resolved. We show that the proposed system can accurately solve nested arithmetical expressions even when trained only on a subset including the simplest cases, significantly outperforming both a sequence-to-sequence model trained end-to-end and a state-of-the-art large language model.
@article{arxiv.2306.17249,
title = {A Hybrid System for Systematic Generalization in Simple Arithmetic Problems},
author = {Flavio Petruzzellis and Alberto Testolin and Alessandro Sperduti},
journal= {arXiv preprint arXiv:2306.17249},
year = {2023}
}
Comments
Accepted at NeSy 2023, 17th International Workshop on Neural-Symbolic Learning and Reasoning