We study the problem of building text classifiers with little or no training data, commonly known as zero and few-shot text classification. In recent years, an approach based on neural textual entailment models has been found to give strong results on a diverse range of tasks. In this work, we show that with proper pre-training, Siamese Networks that embed texts and labels offer a competitive alternative. These models allow for a large reduction in inference cost: constant in the number of labels rather than linear. Furthermore, we introduce label tuning, a simple and computationally efficient approach that allows to adapt the models in a few-shot setup by only changing the label embeddings. While giving lower performance than model fine-tuning, this approach has the architectural advantage that a single encoder can be shared by many different tasks.
@article{arxiv.2203.14655,
title = {Few-Shot Learning with Siamese Networks and Label Tuning},
author = {Thomas Müller and Guillermo Pérez-Torró and Marc Franco-Salvador},
journal= {arXiv preprint arXiv:2203.14655},
year = {2022}
}