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

arXiv: https://arxiv.org/abs/2412.00426 · HTML: https://mlsanity.com/paper/2412.00426/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 60 references that are in the map.
- First posted on arXiv 30 Nov 2024.

## Builds on (most cited first, 12 of 12)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Learning to Compare: Relation Network for Few-Shot Learning](https://mlsanity.com/paper/1711.06025/) (2017)
- [Learning with Fenchel-Young Losses](https://mlsanity.com/paper/1901.02324/) (2019)
- [TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learning](https://mlsanity.com/paper/1905.06549/) (2019)
- [Few-shot Slot Tagging with Collapsed Dependency Transfer and Label-enhanced Task-adaptive Projection Network](https://mlsanity.com/paper/2006.05702/) (2020)
- [Few-shot classification in Named Entity Recognition Task](https://mlsanity.com/paper/1812.06158/) (2018)
- [Eigenvalue and Generalized Eigenvalue Problems: Tutorial](https://mlsanity.com/paper/1903.11240/) (2019)
- [Prompt-Based Metric Learning for Few-Shot NER](https://mlsanity.com/paper/2211.04337/) (2022)
- [Partially Supervised Named Entity Recognition via the Expected Entity Ratio Loss](https://mlsanity.com/paper/2108.07216/) (2021)
- [Transductive Learning for Textual Few-Shot Classification in API-based Embedding Models](https://mlsanity.com/paper/2310.13998/) (2023)

## Abstract (arXiv)

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.