Advancing Transformer's Capabilities in Commonsense Reasoning
This work addresses the disconnect in commonsense reasoning for AI systems, but it is incremental as it applies existing ML methods to improve performance on a specific dataset.
The paper tackled the problem of poor performance of pre-trained language models on commonsense reasoning benchmarks like Com2Sense Dataset by introducing ML-based methods such as knowledge transfer, model ensemble, and a pairwise contrastive objective, resulting in absolute gains of ~15% in Pairwise Accuracy and ~8.7% in Standard Accuracy over previous works.
Recent advances in general purpose pre-trained language models have shown great potential in commonsense reasoning. However, current works still perform poorly on standard commonsense reasoning benchmarks including the Com2Sense Dataset. We argue that this is due to a disconnect with current cutting-edge machine learning methods. In this work, we aim to bridge the gap by introducing current ML-based methods to improve general purpose pre-trained language models in the task of commonsense reasoning. Specifically, we experiment with and systematically evaluate methods including knowledge transfer, model ensemble, and introducing an additional pairwise contrastive objective. Our best model outperforms the strongest previous works by ~15\% absolute gains in Pairwise Accuracy and ~8.7\% absolute gains in Standard Accuracy.