mlsanityData to 7 Oct 2026

Few-shot Named Entity Recognition with Self-describing Networks

arXiv 2203.12252 ↗First posted 23 Mar 2022cs.CLcited by 16

Not on the map. Why?

Abstract (arXiv)

Few-shot NER needs to effectively capture information from limited instances and transfer useful knowledge from external resources. In this paper, we propose a self-describing mechanism for few-shot NER, which can effectively leverage illustrative instances and precisely transfer knowledge from external resources by describing both entity types and mentions using a universal concept set. Specifically, we design Self-describing Networks (SDNet), a Seq2Seq generation model which can universally describe mentions using concepts, automatically map novel entity types to concepts, and adaptively recognize entities on-demand. We pre-train SDNet with large-scale corpus, and conduct experiments on 8 benchmarks from different domains. Experiments show that SDNet achieves competitive performances on all benchmarks and achieves the new state-of-the-art on 6 benchmarks, which demonstrates its effectiveness and robustness.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). Builds on 28 of its 49 references that are in the map. First posted on arXiv 23 Mar 2022.

Builds on

28 of 49 references.

References · 28

  1. 2019A Unified MRC Framework for Named Entity Recognitioncited by 199
  2. 2021Structured Prediction as Translation between Augmented Natural Languagescited by 183
  3. 2016Learning Deep Representations of Fine-grained Visual Descriptionscited by 182
  4. 2021Template-Based Named Entity Recognition Using BARTcited by 153
  5. 2021A Unified Generative Framework for Various NER Subtaskscited by 141
  6. 2021Text2Event: Controllable Sequence-to-Structure Generation for End-to-end Event Extractioncited by 129
  7. 2020Few-shot Slot Tagging with Collapsed Dependency Transfer and Label-enhanced Task-adaptive Projection Networkcited by 83
  8. 2021Template-free Prompt Tuning for Few-shot NERcited by 73
  9. 2018Learning Named Entity Tagger using Domain-Specific Dictionarycited by 65
  10. 2018Few-shot classification in Named Entity Recognition Taskcited by 64
  11. 2021CONTaiNER: Few-Shot Named Entity Recognition via Contrastive Learningcited by 64
  12. 2021Prompt-Learning for Fine-Grained Entity Typingcited by 62
16 more
  1. 2019Distantly Supervised Named Entity Recognition using Positive-Unlabeled Learningcited by 46
  2. 2020Few-Shot Named Entity Recognition: A Comprehensive Studycited by 41
  3. 2016Less is more: zero-shot learning from online textual documents with noise suppressioncited by 40
  4. 2021Ultra-Fine Entity Typing with Weak Supervision from a Masked Language Modelcited by 39
  5. 2021Good Examples Make A Faster Learner: Simple Demonstration-based Learning for Low-resource NERcited by 38
  6. 2019Sequence-to-Nuggets: Nested Entity Mention Detection via Anchor-Region Networkscited by 33
  7. 2020Coarse-to-Fine Pre-training for Named Entity Recognitioncited by 28
  8. 2021De-biasing Distantly Supervised Named Entity Recognition via Causal Interventioncited by 24
  9. 2021Fine-grained Entity Typing via Label Reasoningcited by 22
  10. 2021Learning from Miscellaneous Other-Class Words for Few-shot Named Entity Recognitioncited by 21
  11. 2021Named Entity Recognition with Small Strongly Labeled and Large Weakly Labeled Datacited by 18
  12. 2021Learning from Language Description: Low-shot Named Entity Recognition via Decomposed Frameworkcited by 15
  13. 2018Zero-shot Sequence Labeling: Transferring Knowledge from Sentences to Tokenscited by 12
  14. 2021Denoising Distantly Supervised Named Entity Recognition via a Hypergeometric Probabilistic Modelcited by 7
  15. 2019A Joint Named-Entity Recognizer for Heterogeneous Tag-sets Using a Tag Hierarchycited by 4
  16. 2020One Model to Recognize Them All: Marginal Distillation from NER Models with Different Tag Setscited by 1

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 9; 2024: 4; 2025: 1.

16 papers.

Sort:

By area:

  1. 2023A Dual-way Enhanced Framework from Text Matching Point of View for Multimodal Entity Linkingcited by 11
  2. 2025A Survey on Retrieval And Structuring Augmented Generation with Large Language Modelscited by 8
  3. 2022FactMix: Using a Few Labeled In-domain Examples to Generalize to Cross-domain Named Entity Recognitioncited by 7
  4. 2023Learning In-context Learning for Named Entity Recognitioncited by 7
  5. 2023Less than One-shot: Named Entity Recognition via Extremely Weak Supervisioncited by 4
  6. 2022Disentangling Reasoning Capabilities from Language Models with Compositional Reasoning Transformerscited by 3
  7. 2023Sentence-to-Label Generation Framework for Multi-task Learning of Japanese Sentence Classification and Named Entity Recognitioncited by 3
  8. 2024In-Context Learning for Few-Shot Nested Named Entity Recognitioncited by 3
  9. 2023TKDP: Threefold Knowledge-enriched Deep Prompt Tuning for Few-shot Named Entity Recognitioncited by 2
  10. 2024Large-Scale Label Interpretation Learning for Few-Shot Named Entity Recognitioncited by 2
  11. 2024DWE+: Dual-Way Matching Enhanced Framework for Multimodal Entity Linkingcited by 2
  12. 2023Unleashing the True Potential of Sequence-to-Sequence Models for Sequence Tagging and Structure Parsingcited by 1
4 more
  1. 2023Out-of-Distribution Generalization in Text Classification: Past, Present, and Futurecited by 1
  2. 2023Unifying Token and Span Level Supervisions for Few-Shot Sequence Labelingcited by 1
  3. 2024Few-shot Named Entity Recognition via Superposition Concept Discriminationcited by 1
  4. 2023Mutual Reinforcement Effects in Japanese Sentence Classification and Named Entity Recognition Taskscited by 0