# Few-Shot Named Entity Recognition: A Comprehensive Study

arXiv: https://arxiv.org/abs/2012.14978 · HTML: https://mlsanity.com/paper/2012.14978/

## Key facts

- Cited by 41 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Dec 2020.

## Built on by (most cited first, 30 of 41)

- [Large Language Models for Generative Information Extraction: A Survey](https://mlsanity.com/paper/2312.17617/) (2023)
- [Template-Based Named Entity Recognition Using BART](https://mlsanity.com/paper/2106.01760/) (2021)
- [Few-NERD: A Few-Shot Named Entity Recognition Dataset](https://mlsanity.com/paper/2105.07464/) (2021)
- [Template-free Prompt Tuning for Few-shot NER](https://mlsanity.com/paper/2109.13532/) (2021)
- [CONTaiNER: Few-Shot Named Entity Recognition via Contrastive Learning](https://mlsanity.com/paper/2109.07589/) (2021)
- [Good Examples Make A Faster Learner: Simple Demonstration-based Learning for Low-resource NER](https://mlsanity.com/paper/2110.08454/) (2021)
- [InstructionNER: A Multi-Task Instruction-Based Generative Framework for Few-shot NER](https://mlsanity.com/paper/2203.03903/) (2022)
- [LightNER: A Lightweight Tuning Paradigm for Low-resource NER via Pluggable Prompting](https://mlsanity.com/paper/2109.00720/) (2021)
- [Label Semantics for Few Shot Named Entity Recognition](https://mlsanity.com/paper/2203.08985/) (2022)
- [Question Answering Infused Pre-training of General-Purpose Contextualized Representations](https://mlsanity.com/paper/2106.08190/) (2021)
- [DeepKE: A Deep Learning Based Knowledge Extraction Toolkit for Knowledge Base Population](https://mlsanity.com/paper/2201.03335/) (2022)
- [Few-shot Named Entity Recognition with Entity-level Prototypical Network Enhanced by Dispersedly Distributed Prototypes](https://mlsanity.com/paper/2208.08023/) (2022)
- [Few-shot Named Entity Recognition with Self-describing Networks](https://mlsanity.com/paper/2203.12252/) (2022)
- [Learning from Language Description: Low-shot Named Entity Recognition via Decomposed Framework](https://mlsanity.com/paper/2109.05357/) (2021)
- [QaNER: Prompting Question Answering Models for Few-shot Named Entity Recognition](https://mlsanity.com/paper/2203.01543/) (2022)
- [Research Trends for the Interplay between Large Language Models and Knowledge Graphs](https://mlsanity.com/paper/2406.08223/) (2024)
- [Few-shot learning for medical text: A systematic review](https://mlsanity.com/paper/2204.14081/) (2022)
- [Prompt-Based Metric Learning for Few-Shot NER](https://mlsanity.com/paper/2211.04337/) (2022)
- [LLM-DA: Data Augmentation via Large Language Models for Few-Shot Named Entity Recognition](https://mlsanity.com/paper/2402.14568/) (2024)
- [Towards Few-shot Entity Recognition in Document Images: A Label-aware Sequence-to-Sequence Framework](https://mlsanity.com/paper/2204.05819/) (2022)
- [Few-Shot Fine-Grained Entity Typing with Automatic Label Interpretation and Instance Generation](https://mlsanity.com/paper/2206.13746/) (2022)
- [Large Language Models Vote: Prompting for Rare Disease Identification](https://mlsanity.com/paper/2308.12890/) (2023)
- [Simple Questions Generate Named Entity Recognition Datasets](https://mlsanity.com/paper/2112.08808/) (2021)
- [Inverse is Better! Fast and Accurate Prompt for Few-shot Slot Tagging](https://mlsanity.com/paper/2204.00885/) (2022)
- [Few-Shot Cross-lingual Transfer for Coarse-grained De-identification of Code-Mixed Clinical Texts](https://mlsanity.com/paper/2204.04775/) (2022)
- [Cross-domain Named Entity Recognition via Graph Matching](https://mlsanity.com/paper/2408.00981/) (2024)
- [SEE-Few: Seed, Expand and Entail for Few-shot Named Entity Recognition](https://mlsanity.com/paper/2210.05632/) (2022)
- [Less than One-shot: Named Entity Recognition via Extremely Weak Supervision](https://mlsanity.com/paper/2311.02861/) (2023)
- [Few-Sample Named Entity Recognition for Security Vulnerability Reports by Fine-Tuning Pre-Trained Language Models](https://mlsanity.com/paper/2108.06590/) (2021)
- [In-Context Learning for Few-Shot Nested Named Entity Recognition](https://mlsanity.com/paper/2402.01182/) (2024)

## Abstract (arXiv)

This paper presents a comprehensive study to efficiently build named entity recognition (NER) systems when a small number of in-domain labeled data is available. Based upon recent Transformer-based self-supervised pre-trained language models (PLMs), we investigate three orthogonal schemes to improve the model generalization ability for few-shot settings: (1) meta-learning to construct prototypes for different entity types, (2) supervised pre-training on noisy web data to extract entity-related generic representations and (3) self-training to leverage unlabeled in-domain data. Different combinations of these schemes are also considered. We perform extensive empirical comparisons on 10 public NER datasets with various proportions of labeled data, suggesting useful insights for future research. Our experiments show that (i) in the few-shot learning setting, the proposed NER schemes significantly improve or outperform the commonly used baseline, a PLM-based linear classifier fine-tuned on domain labels; (ii) We create new state-of-the-art results on both few-shot and training-free settings compared with existing methods. We will release our code and pre-trained models for reproducible research.