Contrastive Learning of Sociopragmatic Meaning in Social Media
This work addresses sociopragmatic tasks like emotion and hate speech detection for NLP applications, representing an incremental advance by applying contrastive learning to a specific domain.
The paper tackles the problem of learning sociopragmatic meaning in social media, which involves understanding meaning in interactions across different language communities, and proposes a novel contrastive learning framework that outperforms other methods, achieving an 11.66 average F1 improvement on 16 datasets with only 20 training samples per dataset.
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.Our code is available at: https://github.com/UBC-NLP/infodcl