FastFit: Fast and Effective Few-Shot Text Classification with a Multitude of Classes

Asaf Yehudai, Elron Bandel


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.
Anthology ID:
2024.naacl-demo.18
Volume:
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 3: System Demonstrations)
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Kai-Wei Chang, Annie Lee, Nazneen Rajani
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
174–184
Language:
URL:
https://aclanthology.org/2024.naacl-demo.18
DOI:
Bibkey:
Cite (ACL):
Asaf Yehudai and Elron Bandel. 2024. FastFit: Fast and Effective Few-Shot Text Classification with a Multitude of Classes. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 3: System Demonstrations), pages 174–184, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
FastFit: Fast and Effective Few-Shot Text Classification with a Multitude of Classes (Yehudai & Bandel, NAACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.naacl-demo.18.pdf