PESCO: Prompt-enhanced Self Contrastive Learning for Zero-shot Text Classification
This addresses the problem of text classification without labeled data for researchers and practitioners, offering a novel method with strong performance gains.
The paper tackles zero-shot text classification by introducing PESCO, a contrastive learning framework that uses prompts and self-training to match documents to class labels, achieving 98.5% accuracy on DBpedia without labeled data.
We present PESCO, a novel contrastive learning framework that substantially improves the performance of zero-shot text classification. We formulate text classification as a neural text matching problem where each document is treated as a query, and the system learns the mapping from each query to the relevant class labels by (1) adding prompts to enhance label matching, and (2) using retrieved labels to enrich the training set in a self-training loop of contrastive learning. PESCO achieves state-of-the-art performance on four benchmark text classification datasets. On DBpedia, we achieve 98.5\% accuracy without any labeled data, which is close to the fully-supervised result. Extensive experiments and analyses show all the components of PESCO are necessary for improving the performance of zero-shot text classification.