Go Beyond Plain Fine-Tuning: Improving Pretrained Models for Social Commonsense

Abstract

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, in this study 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.

Data Augmentation for Conversational AI

“…Improvements in these simulators contribute to overall enhancements in dialogue system performance and their ability to handle diverse user inputs and scenarios. Lastly, we explore end-to-end approaches that aim to directly generate dialogue without explicitly defining intermediate steps or modules [4,19,28,32,58]. End-to-end models offer the advantage of encapsulating the entire dialogue generation process within a single model, simplifying both training and inference procedures.…”

A Survey of Reasoning with Foundation Models

“…Another direction in the field of commonsense reasoning involves combining pretrained language models with commonsense-specific fine-tuning techniques. Chang et al (2021) propose several architectural variations, leverage external commonsense corpora, and employ commonsense-specific fine-tuning techniques for the Social IQA task (Sap et al, 2019). Through their work, they demonstrate that these optimizations can enhance the model's performance in tasks related to social intelligence.…”