Not All Negatives are Equal: Label-Aware Contrastive Loss for Fine-grained Text Classification

Understand

Fine-grained classification involves dealing with datasets with larger number of classes with subtle differences between them.

• Guiding the model to focus on differentiating dimensions between these commonly confusable classes is key to improving performance on fine-grained tasks.
• In this work, we analyse the contrastive fine-tuning of pre-trained language models on two fine-grained text classification tasks, emotion classification and sentiment analysis.
• We adaptively embed class relationships into a contrastive objective function to help differently weigh the positives and negatives, and in particular, weighting closely confusable negatives more than less similar negative examples.