Attention Is (not) All You Need for Commonsense Reasoning
This work addresses commonsense reasoning problems for natural language processing, but it is incremental as it builds on an existing model.
The authors tackled commonsense reasoning by re-implementing BERT to use its attention mechanisms for tasks like pronoun disambiguation and the Winograd Schema Challenge, achieving results that outperform the previous state of the art by a margin.
The recently introduced BERT model exhibits strong performance on several language understanding benchmarks. In this paper, we describe a simple re-implementation of BERT for commonsense reasoning. We show that the attentions produced by BERT can be directly utilized for tasks such as the Pronoun Disambiguation Problem and Winograd Schema Challenge. Our proposed attention-guided commonsense reasoning method is conceptually simple yet empirically powerful. Experimental analysis on multiple datasets demonstrates that our proposed system performs remarkably well on all cases while outperforming the previously reported state of the art by a margin. While results suggest that BERT seems to implicitly learn to establish complex relationships between entities, solving commonsense reasoning tasks might require more than unsupervised models learned from huge text corpora.