mlsanityData to 7 Oct 2026

Decomposed Meta-Learning for Few-Shot Named Entity Recognition

arXiv 2204.05751 ↗First posted 12 Apr 2022cs.CLcited by 22

Not on the map. Why?

Abstract (arXiv)

Few-shot named entity recognition (NER) systems aim at recognizing novel-class named entities based on only a few labeled examples. In this paper, we present a decomposed meta-learning approach which addresses the problem of few-shot NER by sequentially tackling few-shot span detection and few-shot entity typing using meta-learning. In particular, we take the few-shot span detection as a sequence labeling problem and train the span detector by introducing the model-agnostic meta-learning (MAML) algorithm to find a good model parameter initialization that could fast adapt to new entity classes. For few-shot entity typing, we propose MAML-ProtoNet, i.e., MAML-enhanced prototypical networks to find a good embedding space that can better distinguish text span representations from different entity classes. Extensive experiments on various benchmarks show that our approach achieves superior performance over prior methods.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). Builds on 31 of its 53 references that are in the map. First posted on arXiv 12 Apr 2022.

Builds on

31 of 53 references.

References · 31

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  4. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  5. 2016Matching Networks for One Shot Learningcited by 2,246
  6. 2020Making Pre-trained Language Models Better Few-shot Learnerscited by 1,255
  7. 2020It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learnerscited by 668
  8. 2016Neural Architectures for Named Entity Recognitioncited by 548
  9. 2016End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRFcited by 341
  10. 2019Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examplescited by 312
  11. 2018FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluationcited by 254
  12. 2015Named Entity Recognition with Bidirectional LSTM-CNNscited by 201
19 more
  1. 2019A Unified MRC Framework for Named Entity Recognitioncited by 199
  2. 2021Template-Based Named Entity Recognition Using BARTcited by 153
  3. 2021Few-NERD: A Few-Shot Named Entity Recognition Datasetcited by 150
  4. 2021A Unified Generative Framework for Various NER Subtaskscited by 141
  5. 2019TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learningcited by 90
  6. 2017Semi-supervised sequence tagging with bidirectional language modelscited by 86
  7. 2020Few-shot Slot Tagging with Collapsed Dependency Transfer and Label-enhanced Task-adaptive Projection Networkcited by 83
  8. 2019Meta Relational Learning for Few-Shot Link Prediction in Knowledge Graphscited by 73
  9. 2018Few-shot classification in Named Entity Recognition Taskcited by 64
  10. 2019Induction Networks for Few-Shot Text Classificationcited by 64
  11. 2021CONTaiNER: Few-Shot Named Entity Recognition via Contrastive Learningcited by 64
  12. 2021SpanNER: Named Entity Re-/Recognition as Span Predictioncited by 55
  13. 2021Few-shot Intent Classification and Slot Filling with Retrieved Examplescited by 35
  14. 2020Augmented Natural Language for Generative Sequence Labelingcited by 29
  15. 2021An Enhanced Span-based Decomposition Method for Few-Shot Sequence Labelingcited by 26
  16. 2019Enhanced Meta-Learning for Cross-lingual Named Entity Recognition with Minimal Resourcescited by 25
  17. 2020Instance-Based Learning of Span Representations: A Case Study through Named Entity Recognitioncited by 23
  18. 2021Learning from Miscellaneous Other-Class Words for Few-shot Named Entity Recognitioncited by 21
  19. 2021Learning from Language Description: Low-shot Named Entity Recognition via Decomposed Frameworkcited by 15

Built on by

Cited by year

Citing papers per year: 2022: 4; 2023: 10; 2024: 4; 2025: 4.

22 papers.

Sort:

  1. 2023NBIAS: A Natural Language Processing Framework for Bias Identification in Textcited by 23
  2. 2024Few-shot Name Entity Recognition on StackOverflowcited by 14
  3. 2022Prompt-Based Metric Learning for Few-Shot NERcited by 12
  4. 2023A Multi-Task Semantic Decomposition Framework with Task-specific Pre-training for Few-Shot NERcited by 9
  5. 2022SpanProto: A Two-stage Span-based Prototypical Network for Few-shot Named Entity Recognitioncited by 8
  6. 2025ChatPD: An LLM-driven Paper-Dataset Networking Systemcited by 7
  7. 2023A Prototypical Semantic Decoupling Method via Joint Contrastive Learning for Few-Shot Name Entity Recognitioncited by 6
  8. 2023UniEX: An Effective and Efficient Framework for Unified Information Extraction via a Span-extractive Perspectivecited by 6
  9. 2023PromptNER: A Prompting Method for Few-shot Named Entity Recognition via k Nearest Neighbor Searchcited by 4
  10. 2023Uncertainty-aware Self-training for Low-resource Neural Sequence Labelingcited by 3
  11. 2024Fighting Against the Repetitive Training and Sample Dependency Problem in Few-shot Named Entity Recognitioncited by 3
  12. 2022Win-Win Cooperation: Bundling Sequence and Span Models for Named Entity Recognitioncited by 2
10 more
  1. 2022Few-Shot Nested Named Entity Recognitioncited by 2
  2. 2023ProKD: An Unsupervised Prototypical Knowledge Distillation Network for Zero-Resource Cross-Lingual Named Entity Recognitioncited by 2
  3. 2023Meta-Learning Triplet Network with Adaptive Margins for Few-Shot Named Entity Recognitioncited by 1
  4. 2023Unifying Token and Span Level Supervisions for Few-Shot Sequence Labelingcited by 1
  5. 2025FewTopNER: Integrating Few-Shot Learning with Topic Modeling and Named Entity Recognition in a Multilingual Frameworkcited by 1
  6. 2023Causal Interventions-based Few-Shot Named Entity Recognitioncited by 0
  7. 2024Hybrid Multi-stage Decoding for Few-shot NER with Entity-aware Contrastive Learningcited by 0
  8. 2024A Unified Label-Aware Contrastive Learning Framework for Few-Shot Named Entity Recognitioncited by 0
  9. 2025ReProCon: Scalable and Resource-Efficient Few-Shot Biomedical Named Entity Recognitioncited by 0
  10. 2025Named Entity Recognition in COVID-19 tweets with Entity Knowledge Augmentationcited by 0