Few-Shot Domain Adaptation for Named-Entity Recognition via Joint Constrained k-Means and Subspace Selection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hammal, Ayoub, Uthayasooriyar, Benno, Corro, Caio
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910741803565056
author Hammal, Ayoub
Uthayasooriyar, Benno
Corro, Caio
author_facet Hammal, Ayoub
Uthayasooriyar, Benno
Corro, Caio
contents 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 on several English datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2412_00426
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Few-Shot Domain Adaptation for Named-Entity Recognition via Joint Constrained k-Means and Subspace Selection
Hammal, Ayoub
Uthayasooriyar, Benno
Corro, Caio
Computation and Language
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 on several English datasets.
title Few-Shot Domain Adaptation for Named-Entity Recognition via Joint Constrained k-Means and Subspace Selection
topic Computation and Language
url https://arxiv.org/abs/2412.00426