@inproceedings{muller-etal-2022-shot,
    title = "Few-Shot Learning with {S}iamese Networks and Label Tuning",
    author = {M{\"u}ller, Thomas  and
      P{\'e}rez-Torr{\'o}, Guillermo  and
      Franco-Salvador, Marc},
    editor = "Muresan, Smaranda  and
      Nakov, Preslav  and
      Villavicencio, Aline",
    booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = may,
    year = "2022",
    address = "Dublin, Ireland",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2022.acl-long.584/",
    doi = "10.18653/v1/2022.acl-long.584",
    pages = "8532--8545",
    abstract = "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."
}