Recent progress in representation and contrastive learning in NLP has not widely considered the class of \textit{sociopragmatic meaning} (i.e., meaning in interaction within different language communities). To bridge this gap, we propose a novel framework for learning task-agnostic representations transferable to a wide range of sociopragmatic tasks (e.g., emotion, hate speech, humor, sarcasm). Our framework outperforms other contrastive learning frameworks for both in-domain and out-of-domain data, across both the general and few-shot settings. For example, compared to two popular pre-trained language models, our method obtains an improvement of $11.66$ average $F_1$ on $16$ datasets when fine-tuned on only $20$ training samples per dataset.

翻译：近期自然语言处理中表示学习和对比学习的进展并未广泛考虑\textit{社会语用意义}（即不同语言社区内的交互意义）。为弥补这一空白，我们提出了一种新颖的框架，用于学习任务无关的表示，可迁移至广泛的社会语用任务（例如，情感、仇恨言论、幽默、讽刺）。我们的框架在域内和域外数据上，以及在一般和少样本设置下，均优于其他对比学习框架。例如，与两种流行的预训练语言模型相比，我们的方法在每数据集仅使用20个训练样本进行微调时，在16个数据集上平均$F_1$值提升了$11.66$。