Go Beyond Plain Fine-tuning: Improving Pretrained Models for Social Commonsense
This work addresses the need for better social commonsense reasoning in NLP, but it is incremental as it builds on existing models and datasets.
The authors tackled the problem of improving pretrained language models' social intelligence by focusing on the Social IQA dataset, achieving competitive results comparable to top-ranking models on the leaderboard.
Pretrained language models have demonstrated outstanding performance in many NLP tasks recently. However, their social intelligence, which requires commonsense reasoning about the current situation and mental states of others, is still developing. Towards improving language models' social intelligence, we focus on the Social IQA dataset, a task requiring social and emotional commonsense reasoning. Building on top of the pretrained RoBERTa and GPT2 models, we propose several architecture variations and extensions, as well as leveraging external commonsense corpora, to optimize the model for Social IQA. Our proposed system achieves competitive results as those top-ranking models on the leaderboard. This work demonstrates the strengths of pretrained language models, and provides viable ways to improve their performance for a particular task.