# Simple and Effective Few-Shot Named Entity Recognition with Structured Nearest Neighbor Learning

arXiv: https://arxiv.org/abs/2010.02405 · HTML: https://mlsanity.com/paper/2010.02405/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Oct 2020.

## Built on by (most cited first, 6 of 6)

- [Neural Data Augmentation via Example Extrapolation](https://mlsanity.com/paper/2102.01335/) (2021)
- [A Prototypical Semantic Decoupling Method via Joint Contrastive Learning for Few-Shot Name Entity Recognition](https://mlsanity.com/paper/2302.13610/) (2023)
- [Few-Sample Named Entity Recognition for Security Vulnerability Reports by Fine-Tuning Pre-Trained Language Models](https://mlsanity.com/paper/2108.06590/) (2021)
- [Few-Shot Joint Multimodal Entity-Relation Extraction via Knowledge-Enhanced Cross-modal Prompt Model](https://mlsanity.com/paper/2410.14225/) (2024)
- [A Sequence Tagging based Framework for Few-Shot Relation Extraction](https://mlsanity.com/paper/2208.08053/) (2022)
- [Hybrid Multi-stage Decoding for Few-shot NER with Entity-aware Contrastive Learning](https://mlsanity.com/paper/2404.06970/) (2024)

## Abstract (arXiv)

We present a simple few-shot named entity recognition (NER) system based on nearest neighbor learning and structured inference. Our system uses a supervised NER model trained on the source domain, as a feature extractor. Across several test domains, we show that a nearest neighbor classifier in this feature-space is far more effective than the standard meta-learning approaches. We further propose a cheap but effective method to capture the label dependencies between entity tags without expensive CRF training. We show that our method of combining structured decoding with nearest neighbor learning achieves state-of-the-art performance on standard few-shot NER evaluation tasks, improving F1 scores by 6% to 16% absolute points over prior meta-learning based systems.