Anchoring Fine-tuning of Sentence Transformer with Semantic Label Information for Efficient Truly Few-shot Classification

Amalie Pauli, Leon Derczynski, Ira Assent


Abstract
Few-shot classification is a powerful technique, but training requires substantial computing power and data. We propose an efficient method with small model sizes and less training data with only 2-8 training instances per class. Our proposed method, AncSetFit, targets low data scenarios by anchoring the task and label information through sentence embeddings in fine-tuning a Sentence Transformer model. It uses contrastive learning and a triplet loss to enforce training instances of a class to be closest to its own textual semantic label information in the embedding space - and thereby learning to embed different class instances more distinct. AncSetFit obtains strong performance in data-sparse scenarios compared to existing methods across SST-5, Emotion detection, and AG News data, even with just two examples per class.
Anthology ID:
2023.emnlp-main.692
Volume:
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
11254–11264
Language:
URL:
https://aclanthology.org/2023.emnlp-main.692
DOI:
10.18653/v1/2023.emnlp-main.692
Bibkey:
Cite (ACL):
Amalie Pauli, Leon Derczynski, and Ira Assent. 2023. Anchoring Fine-tuning of Sentence Transformer with Semantic Label Information for Efficient Truly Few-shot Classification. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 11254–11264, Singapore. Association for Computational Linguistics.
Cite (Informal):
Anchoring Fine-tuning of Sentence Transformer with Semantic Label Information for Efficient Truly Few-shot Classification (Pauli et al., EMNLP 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-acl-2023-videos/2023.emnlp-main.692.pdf