mlsanityData to 7 Oct 2026

An Enhanced Span-based Decomposition Method for Few-Shot Sequence Labeling

arXiv 2109.13023 ↗First posted 27 Sep 2021cs.CLcited by 26

Not on the map. Why?

Abstract (arXiv)

Few-Shot Sequence Labeling (FSSL) is a canonical paradigm for the tagging models, e.g., named entity recognition and slot filling, to generalize on an emerging, resource-scarce domain. Recently, the metric-based meta-learning framework has been recognized as a promising approach for FSSL. However, most prior works assign a label to each token based on the token-level similarities, which ignores the integrality of named entities or slots. To this end, in this paper, we propose ESD, an Enhanced Span-based Decomposition method for FSSL. ESD formulates FSSL as a span-level matching problem between test query and supporting instances. Specifically, ESD decomposes the span matching problem into a series of span-level procedures, mainly including enhanced span representation, class prototype aggregation and span conflicts resolution. Extensive experiments show that ESD achieves the new state-of-the-art results on two popular FSSL benchmarks, FewNERD and SNIPS, and is proven to be more robust in the nested and noisy tagging scenarios. Our code is available at https://github.com/Wangpeiyi9979/ESD.

Key facts. Cited by 26 papers in the map (data through 7 Oct 2026). Builds on 25 of its 35 references that are in the map. First posted on arXiv 27 Sep 2021.

Builds on

25 of 35 references.

References · 25

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  4. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  5. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  6. 2016Layer Normalizationcited by 5,579
  7. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  8. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  9. 2016Matching Networks for One Shot Learningcited by 2,246
  10. 2019SpanBERT: Improving Pre-training by Representing and Predicting Spanscited by 832
  11. 2019Generalizing from a Few Examples: A Survey on Few-Shot Learningcited by 462
  12. 2017Soft-NMS -- Improving Object Detection With One Line of Codecited by 380
13 more
  1. 2018Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfacescited by 376
  2. 2018FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluationcited by 254
  3. 2021Template-Based Named Entity Recognition Using BARTcited by 153
  4. 2021Few-NERD: A Few-Shot Named Entity Recognition Datasetcited by 150
  5. 2019TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learningcited by 90
  6. 2020Few-shot Slot Tagging with Collapsed Dependency Transfer and Label-enhanced Task-adaptive Projection Networkcited by 83
  7. 2018Few-shot classification in Named Entity Recognition Taskcited by 64
  8. 2019Induction Networks for Few-Shot Text Classificationcited by 64
  9. 2021Locate and Label: A Two-stage Identifier for Nested Named Entity Recognitioncited by 60
  10. 2021Few-shot Intent Classification and Slot Filling with Retrieved Examplescited by 35
  11. 2020Augmented Natural Language for Generative Sequence Labelingcited by 29
  12. 2020ConVEx: Data-Efficient and Few-Shot Slot Labelingcited by 22
  13. 2021Behind the Scenes: An Exploration of Trigger Biases Problem in Few-Shot Event Classificationcited by 8

Built on by

Cited by year

Citing papers per year: 2022: 7; 2023: 12; 2024: 6; 2025: 1.

26 papers.

Sort:

  1. 2022Decomposed Meta-Learning for Few-Shot Named Entity Recognitioncited by 22
  2. 2022Few-shot Named Entity Recognition with Entity-level Prototypical Network Enhanced by Dispersedly Distributed Prototypescited by 17
  3. 2022Prompt-Based Metric Learning for Few-Shot NERcited by 12
  4. 2023VicunaNER: Zero/Few-shot Named Entity Recognition using Vicunacited by 9
  5. 2023A Multi-Task Semantic Decomposition Framework with Task-specific Pre-training for Few-Shot NERcited by 9
  6. 2022SpanProto: A Two-stage Span-based Prototypical Network for Few-shot Named Entity Recognitioncited by 8
  7. 2023Learning In-context Learning for Named Entity Recognitioncited by 7
  8. 2023A Prototypical Semantic Decoupling Method via Joint Contrastive Learning for Few-Shot Name Entity Recognitioncited by 6
  9. 2023UniEX: An Effective and Efficient Framework for Unified Information Extraction via a Span-extractive Perspectivecited by 6
  10. 2023Type-Aware Decomposed Framework for Few-Shot Named Entity Recognitioncited by 4
  11. 2023PromptNER: A Prompting Method for Few-shot Named Entity Recognition via k Nearest Neighbor Searchcited by 4
  12. 2023Robust Few-Shot Named Entity Recognition with Boundary Discrimination and Correlation Purificationcited by 4
14 more
  1. 2022A Unified Framework for Multi-intent Spoken Language Understanding with promptingcited by 3
  2. 2024In-Context Learning for Few-Shot Nested Named Entity Recognitioncited by 3
  3. 2024Fighting Against the Repetitive Training and Sample Dependency Problem in Few-shot Named Entity Recognitioncited by 3
  4. 2024BANER: Boundary-Aware LLMs for Few-Shot Named Entity Recognitioncited by 3
  5. 2025MISE: Meta-knowledge Inheritance for Social Media-Based Stressor Estimationcited by 3
  6. 2022Few-shot Classification with Hypersphere Modeling of Prototypescited by 2
  7. 2022Few-Shot Nested Named Entity Recognitioncited by 2
  8. 2024Large-Scale Label Interpretation Learning for Few-Shot Named Entity Recognitioncited by 2
  9. 2023Meta-Learning Triplet Network with Adaptive Margins for Few-Shot Named Entity Recognitioncited by 1
  10. 2023Unifying Token and Span Level Supervisions for Few-Shot Sequence Labelingcited by 1
  11. 2023Enhancing Low-resource Fine-grained Named Entity Recognition by Leveraging Coarse-grained Datasetscited by 1
  12. 2024Few-shot Named Entity Recognition via Superposition Concept Discriminationcited by 1
  13. 2023Causal Interventions-based Few-Shot Named Entity Recognitioncited by 0
  14. 2024Hybrid Multi-stage Decoding for Few-shot NER with Entity-aware Contrastive Learningcited by 0