mlsanityData to 7 Oct 2026

Few-shot Named Entity Recognition via Superposition Concept Discrimination

arXiv 2403.16463 ↗First posted 25 Mar 2024cs.CLcited by 1

Not on the map. Why?

Abstract (arXiv)

Few-shot NER aims to identify entities of target types with only limited number of illustrative instances. Unfortunately, few-shot NER is severely challenged by the intrinsic precise generalization problem, i.e., it is hard to accurately determine the desired target type due to the ambiguity stemming from information deficiency. In this paper, we propose Superposition Concept Discriminator (SuperCD), which resolves the above challenge via an active learning paradigm. Specifically, a concept extractor is first introduced to identify superposition concepts from illustrative instances, with each concept corresponding to a possible generalization boundary. Then a superposition instance retriever is applied to retrieve corresponding instances of these superposition concepts from large-scale text corpus. Finally, annotators are asked to annotate the retrieved instances and these annotated instances together with original illustrative instances are used to learn FS-NER models. To this end, we learn a universal concept extractor and superposition instance retriever using a large-scale openly available knowledge bases. Experiments show that SuperCD can effectively identify superposition concepts from illustrative instances, retrieve superposition instances from large-scale corpus, and significantly improve the few-shot NER performance with minimal additional efforts.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 22 of its 38 references that are in the map. First posted on arXiv 25 Mar 2024.

Builds on

22 of 38 references.

References · 22

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  3. 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 602
  4. 2019Entity, Relation, and Event Extraction with Contextualized Span Representationscited by 261
  5. 2022Selective Annotation Makes Language Models Better Few-Shot Learnerscited by 242
  6. 2021Active Learning by Acquiring Contrastive Examplescited by 154
  7. 2021Template-Based Named Entity Recognition Using BARTcited by 153
  8. 2021Few-NERD: A Few-Shot Named Entity Recognition Datasetcited by 150
  9. 2020Cold-start Active Learning through Self-supervised Language Modelingcited by 128
  10. 2017Deep Active Learning for Named Entity Recognitioncited by 108
  11. 2020Few-shot Slot Tagging with Collapsed Dependency Transfer and Label-enhanced Task-adaptive Projection Networkcited by 83
  12. 2021Template-free Prompt Tuning for Few-shot NERcited by 73
10 more
  1. 2018Few-shot classification in Named Entity Recognition Taskcited by 64
  2. 2021CONTaiNER: Few-Shot Named Entity Recognition via Contrastive Learningcited by 64
  3. 2021Good Examples Make A Faster Learner: Simple Demonstration-based Learning for Low-resource NERcited by 38
  4. 2021An Enhanced Span-based Decomposition Method for Few-Shot Sequence Labelingcited by 26
  5. 2021Learning from Miscellaneous Other-Class Words for Few-shot Named Entity Recognitioncited by 21
  6. 2022Few-shot Named Entity Recognition with Entity-level Prototypical Network Enhanced by Dispersedly Distributed Prototypescited by 17
  7. 2022Few-shot Named Entity Recognition with Self-describing Networkscited by 16
  8. 2021Learning from Language Description: Low-shot Named Entity Recognition via Decomposed Frameworkcited by 15
  9. 2020Deep Active Learning for Sequence Labeling Based on Diversity and Uncertainty in Gradientcited by 8
  10. 2022FAMIE: A Fast Active Learning Framework for Multilingual Information Extractioncited by 8

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025SAFR: Neuron Redistribution for Interpretabilitycited by 2