FastFit: Fast and Effective Few-Shot Text Classification with a Multitude of Classes
Abstract
We present FastFit, a Python package designed to provide fast and accurate few-shot classification, especially for scenarios with many semantically similar classes. FastFit utilizes a novel approach integrating batch contrastive learning and token-level similarity score. Compared to existing few-shot learning packages, such as SetFit, Transformers, or few-shot prompting of large language models via API calls, FastFit significantly improves multi-class classification performance in speed and accuracy across various English and Multilingual datasets. FastFit demonstrates a 3-20x improvement in training speed, completing training in just a few seconds. The FastFit package is now available on GitHub, presenting a user-friendly solution for NLP practitioners.
BibTeX
@inproceedings{yehudai-bandel-2024-fastfit,
title = "{F}ast{F}it: Fast and Effective Few-Shot Text Classification with a Multitude of Classes",
author = "Yehudai, Asaf and
Bandel, Elron",
editor = "Chang, Kai-Wei and
Lee, Annie and
Rajani, Nazneen",
booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 3: System Demonstrations)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.naacl-demo.18/",
doi = "10.18653/v1/2024.naacl-demo.18",
pages = "174--184"
}