# SpanProto: A Two-stage Span-based Prototypical Network for Few-shot Named Entity Recognition

arXiv: https://arxiv.org/abs/2210.09049 · HTML: https://mlsanity.com/paper/2210.09049/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 48 references that are in the map.
- First posted on arXiv 17 Oct 2022.

## Builds on (most cited first, 29 of 29)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [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)
- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks](https://mlsanity.com/paper/1901.11196/) (2019)
- [Neural Architectures for Named Entity Recognition](https://mlsanity.com/paper/1603.01360/) (2016)
- [Bidirectional LSTM-CRF Models for Sequence Tagging](https://mlsanity.com/paper/1508.01991/) (2015)
- [End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF](https://mlsanity.com/paper/1603.01354/) (2016)
- [Few-NERD: A Few-Shot Named Entity Recognition Dataset](https://mlsanity.com/paper/2105.07464/) (2021)
- [Named Entity Recognition as Dependency Parsing](https://mlsanity.com/paper/2005.07150/) (2020)
- [A Survey of Deep Meta-Learning](https://mlsanity.com/paper/2010.03522/) (2020)
- [Semi-supervised sequence tagging with bidirectional language models](https://mlsanity.com/paper/1705.00108/) (2017)
- [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)
- [CONTaiNER: Few-Shot Named Entity Recognition via Contrastive Learning](https://mlsanity.com/paper/2109.07589/) (2021)
- [Locate and Label: A Two-stage Identifier for Nested Named Entity Recognition](https://mlsanity.com/paper/2105.06804/) (2021)
- [Adaptive Attentional Network for Few-Shot Knowledge Graph Completion](https://mlsanity.com/paper/2010.09638/) (2020)
- [An Enhanced Span-based Decomposition Method for Few-Shot Sequence Labeling](https://mlsanity.com/paper/2109.13023/) (2021)
- [Dynamic Memory Induction Networks for Few-Shot Text Classification](https://mlsanity.com/paper/2005.05727/) (2020)
- [Decomposed Meta-Learning for Few-Shot Named Entity Recognition](https://mlsanity.com/paper/2204.05751/) (2022)
- [Label Semantics for Few Shot Named Entity Recognition](https://mlsanity.com/paper/2203.08985/) (2022)
- [Example-Based Named Entity Recognition](https://mlsanity.com/paper/2008.10570/) (2020)
- [Rethinking preventing class-collapsing in metric learning with margin-based losses](https://mlsanity.com/paper/2006.05162/) (2020)
- [EasyNLP: A Comprehensive and Easy-to-use Toolkit for Natural Language Processing](https://mlsanity.com/paper/2205.00258/) (2022)
- [Propose-and-Refine: A Two-Stage Set Prediction Network for Nested Named Entity Recognition](https://mlsanity.com/paper/2204.12732/) (2022)
- [KECP: Knowledge Enhanced Contrastive Prompting for Few-shot Extractive Question Answering](https://mlsanity.com/paper/2205.03071/) (2022)
- [Domain Adaptation for Named Entity Recognition in Online Media with Word Embeddings](https://mlsanity.com/paper/1612.00148/) (2016)

## Built on by (most cited first, 8 of 8)

- [A Multi-Task Semantic Decomposition Framework with Task-specific Pre-training for Few-Shot NER](https://mlsanity.com/paper/2308.14533/) (2023)
- [Improving Self-training for Cross-lingual Named Entity Recognition with Contrastive and Prototype Learning](https://mlsanity.com/paper/2305.13628/) (2023)
- [PromptNER: A Prompting Method for Few-shot Named Entity Recognition via k Nearest Neighbor Search](https://mlsanity.com/paper/2305.12217/) (2023)
- [DemoNSF: A Multi-task Demonstration-based Generative Framework for Noisy Slot Filling Task](https://mlsanity.com/paper/2310.10169/) (2023)
- [Meta-Learning Triplet Network with Adaptive Margins for Few-Shot Named Entity Recognition](https://mlsanity.com/paper/2302.07739/) (2023)
- [FewTopNER: Integrating Few-Shot Learning with Topic Modeling and Named Entity Recognition in a Multilingual Framework](https://mlsanity.com/paper/2502.02391/) (2025)
- [ReProCon: Scalable and Resource-Efficient Few-Shot Biomedical Named Entity Recognition](https://mlsanity.com/paper/2508.16833/) (2025)
- [Enhancing Scientific Named Entity Recognition via Large Language Models: A Type-driven Multi-task Learning Approach](https://mlsanity.com/paper/2608.08636/) (2026)

## Abstract (arXiv)

Few-shot Named Entity Recognition (NER) aims to identify named entities with very little annotated data. Previous methods solve this problem based on token-wise classification, which ignores the information of entity boundaries, and inevitably the performance is affected by the massive non-entity tokens. To this end, we propose a seminal span-based prototypical network (SpanProto) that tackles few-shot NER via a two-stage approach, including span extraction and mention classification. In the span extraction stage, we transform the sequential tags into a global boundary matrix, enabling the model to focus on the explicit boundary information. For mention classification, we leverage prototypical learning to capture the semantic representations for each labeled span and make the model better adapt to novel-class entities. To further improve the model performance, we split out the false positives generated by the span extractor but not labeled in the current episode set, and then present a margin-based loss to separate them from each prototype region. Experiments over multiple benchmarks demonstrate that our model outperforms strong baselines by a large margin.