Few-shot domain adaptation for named-entity recognition via joint constrained k-means and subspace selection

Ayoub Hammal, Benno Uthayasooriyar, Caio Corro


Abstract
Named-entity recognition (NER) is a task that typically requires large annotated datasets, which limits its applicability across domains with varying entity definitions. This paper addresses few-shot NER, aiming to transfer knowledge to new domains with minimal supervision. Unlike previous approaches that rely solely on limited annotated data, we propose a weakly-supervised algorithm that combines small labeled datasets with large amounts of unlabeled data. Our method extends the k-means algorithm with label supervision, cluster size constraints, and domain-specific discriminative subspace selection. This unified framework achieves state-of-the-art results in few-shot NER, demonstrating its effectiveness in leveraging unlabeled data and adapting to domain-specific challenges.
Anthology ID:
2025.coling-main.662
Volume:
Proceedings of the 31st International Conference on Computational Linguistics
Month:
January
Year:
2025
Address:
Abu Dhabi, UAE
Editors:
Owen Rambow, Leo Wanner, Marianna Apidianaki, Hend Al-Khalifa, Barbara Di Eugenio, Steven Schockaert
Venue:
COLING
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
9902–9916
Language:
URL:
https://aclanthology.org/2025.coling-main.662/
DOI:
Bibkey:
Cite (ACL):
Ayoub Hammal, Benno Uthayasooriyar, and Caio Corro. 2025. Few-shot domain adaptation for named-entity recognition via joint constrained k-means and subspace selection. In Proceedings of the 31st International Conference on Computational Linguistics, pages 9902–9916, Abu Dhabi, UAE. Association for Computational Linguistics.
Cite (Informal):
Few-shot domain adaptation for named-entity recognition via joint constrained k-means and subspace selection (Hammal et al., COLING 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.coling-main.662.pdf