English

Explain Yourself! Leveraging Language Models for Commonsense Reasoning

Computation and Language 2019-06-07 v1

Abstract

Deep learning models perform poorly on tasks that require commonsense reasoning, which often necessitates some form of world-knowledge or reasoning over information not immediately present in the input. We collect human explanations for commonsense reasoning in the form of natural language sequences and highlighted annotations in a new dataset called Common Sense Explanations (CoS-E). We use CoS-E to train language models to automatically generate explanations that can be used during training and inference in a novel Commonsense Auto-Generated Explanation (CAGE) framework. CAGE improves the state-of-the-art by 10% on the challenging CommonsenseQA task. We further study commonsense reasoning in DNNs using both human and auto-generated explanations including transfer to out-of-domain tasks. Empirical results indicate that we can effectively leverage language models for commonsense reasoning.

Keywords

Cite

@article{arxiv.1906.02361,
  title  = {Explain Yourself! Leveraging Language Models for Commonsense Reasoning},
  author = {Nazneen Fatema Rajani and Bryan McCann and Caiming Xiong and Richard Socher},
  journal= {arXiv preprint arXiv:1906.02361},
  year   = {2019}
}

Comments

Accepted at ACL, 11 pages total

R2 v1 2026-06-23T09:44:33.761Z