mlsanityData to 14 Oct 2026

Good Examples Make A Faster Learner: Simple Demonstration-based Learning for Low-resource NER

arXiv 2110.08454 ↗First posted 16 Oct 2021cs.CLcited by 38

Not on the map. Why?

Abstract (arXiv)

Recent advances in prompt-based learning have shown strong results on few-shot text classification by using cloze-style templates. Similar attempts have been made on named entity recognition (NER) which manually design templates to predict entity types for every text span in a sentence. However, such methods may suffer from error propagation induced by entity span detection, high cost due to enumeration of all possible text spans, and omission of inter-dependencies among token labels in a sentence. Here we present a simple demonstration-based learning method for NER, which lets the input be prefaced by task demonstrations for in-context learning. We perform a systematic study on demonstration strategy regarding what to include (entity examples, with or without surrounding context), how to select the examples, and what templates to use. Results on in-domain learning and domain adaptation show that the model's performance in low-resource settings can be largely improved with a suitable demonstration strategy (e.g., a 4-17% improvement on 25 train instances). We also find that good demonstration can save many labeled examples and consistency in demonstration contributes to better performance.

Key facts. Cited by 38 papers in the map (data through 14 Oct 2026). Builds on 32 of its 51 references that are in the map. First posted on arXiv 16 Oct 2021.

Builds on

32 of 51 references.

References · 32

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  4. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,512
  5. 2021Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processingcited by 2,234
  6. 2019Language Models as Knowledge Bases?cited by 1,936
  7. 2020Don't Stop Pretraining: Adapt Language Models to Domains and Taskscited by 1,565
  8. 2021Calibrate Before Use: Improving Few-Shot Performance of Language Modelscited by 1,392
  9. 2020Making Pre-trained Language Models Better Few-shot Learnerscited by 1,256
  10. 2019How Can We Know What Language Models Know?cited by 959
  11. 2020Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inferencecited by 938
  12. 2021BARTScore: Evaluating Generated Text as Text Generationcited by 722
20 more
  1. 2016Neural Architectures for Named Entity Recognitioncited by 550
  2. 2016End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRFcited by 341
  3. 2015Named Entity Recognition with Bidirectional LSTM-CNNscited by 201
  4. 2021Structured Prediction as Translation between Augmented Natural Languagescited by 183
  5. 2020How Context Affects Language Models' Factual Predictionscited by 181
  6. 2021Template-Based Named Entity Recognition Using BARTcited by 153
  7. 2021Few-NERD: A Few-Shot Named Entity Recognition Datasetcited by 152
  8. 2020Automatically Identifying Words That Can Serve as Labels for Few-Shot Text Classificationcited by 98
  9. 2021BERTese: Learning to Speak to BERTcited by 82
  10. 2021Improving Named Entity Recognition by External Context Retrieving and Cooperative Learningcited by 76
  11. 2018Learning Named Entity Tagger using Domain-Specific Dictionarycited by 65
  12. 2021Prompt-Learning for Fine-Grained Entity Typingcited by 62
  13. 2021Reordering Examples Helps during Priming-based Few-Shot Learningcited by 50
  14. 2019Distantly Supervised Named Entity Recognition using Positive-Unlabeled Learningcited by 46
  15. 2020Few-Shot Named Entity Recognition: A Comprehensive Studycited by 41
  16. 2021Distantly-Supervised Named Entity Recognition with Noise-Robust Learning and Language Model Augmented Self-Trainingcited by 41
  17. 2020TriggerNER: Learning with Entity Triggers as Explanations for Named Entity Recognitioncited by 30
  18. 2017Empower Sequence Labeling with Task-Aware Neural Language Modelcited by 28
  19. 2020Improving Named Entity Recognition with Attentive Ensemble of Syntactic Informationcited by 17
  20. 2020LEAN-LIFE: A Label-Efficient Annotation Framework Towards Learning from Explanationcited by 11

Built on by

Cited by year

Citing papers per year: 2022: 11; 2023: 18; 2024: 8; 2025: 1.

38 papers.

Sort:

By area:

  1. 2023Exploring Effective Factors for Improving Visual In-Context Learningcited by 43
  2. 2022Decoupling Knowledge from Memorization: Retrieval-augmented Prompt Learningcited by 36
  3. 2023PromptNER: Prompting For Named Entity Recognitioncited by 35
  4. 2023The Life Cycle of Knowledge in Big Language Models: A Surveycited by 23
  5. 2023PromptNER: Prompt Locating and Typing for Named Entity Recognitioncited by 17
  6. 2022Few-shot Named Entity Recognition with Self-describing Networkscited by 16
  7. 2022Prompt-Based Metric Learning for Few-Shot NERcited by 12
  8. 2024Few-shot clinical entity recognition in English, French and Spanish: masked language models outperform generative model promptingcited by 12
  9. 2022Domain-Specific NER via Retrieving Correlated Samplescited by 11
  10. 2022Robustness of Demonstration-based Learning Under Limited Data Scenariocited by 11
  11. 2023Prompting ChatGPT in MNER: Enhanced Multimodal Named Entity Recognition with Auxiliary Refined Knowledgecited by 11
  12. 2022Information Extraction in Low-Resource Scenarios: Survey and Perspectivecited by 10
26 more
  1. 2022Few-Shot Fine-Grained Entity Typing with Automatic Label Interpretation and Instance Generationcited by 9
  2. 2023A Multi-Task Semantic Decomposition Framework with Task-specific Pre-training for Few-Shot NERcited by 9
  3. 2023A Survey on Arabic Named Entity Recognition: Past, Recent Advances, and Future Trendscited by 8
  4. 2022Contrastive Demonstration Tuning for Pre-trained Language Modelscited by 7
  5. 2022FactMix: Using a Few Labeled In-domain Examples to Generalize to Cross-domain Named Entity Recognitioncited by 7
  6. 2022Can You Label Less by Using Out-of-Domain Data? Active & Transfer Learning with Few-shot Instructionscited by 7
  7. 2023Learning In-context Learning for Named Entity Recognitioncited by 7
  8. 2023DemoNSF: A Multi-task Demonstration-based Generative Framework for Noisy Slot Filling Taskcited by 5
  9. 2023DemoSG: Demonstration-enhanced Schema-guided Generation for Low-resource Event Extractioncited by 5
  10. 2024P-ICL: Point In-Context Learning for Named Entity Recognition with Large Language Modelscited by 5
  11. 2023Type-Aware Decomposed Framework for Few-Shot Named Entity Recognitioncited by 4
  12. 2023Less than One-shot: Named Entity Recognition via Extremely Weak Supervisioncited by 4
  13. 2024BANER: Boundary-Aware LLMs for Few-Shot Named Entity Recognitioncited by 3
  14. 2023TKDP: Threefold Knowledge-enriched Deep Prompt Tuning for Few-shot Named Entity Recognitioncited by 2
  15. 2024Large-Scale Label Interpretation Learning for Few-Shot Named Entity Recognitioncited by 2
  16. 2024PICLe: Pseudo-Annotations for In-Context Learning in Low-Resource Named Entity Detectioncited by 2
  17. 2023Out-of-Distribution Generalization in Text Classification: Past, Present, and Futurecited by 1
  18. 2023Unifying Token and Span Level Supervisions for Few-Shot Sequence Labelingcited by 1
  19. 2023Demonstration-based learning for few-shot biomedical named entity recognition under machine reading comprehensioncited by 1
  20. 2023Labels Need Prompts Too: Mask Matching for Natural Language Understanding Taskscited by 1
  21. 2024Chem-FINESE: Validating Fine-Grained Few-shot Entity Extraction through Text Reconstructioncited by 1
  22. 2024Few-shot Named Entity Recognition via Superposition Concept Discriminationcited by 1
  23. 2022A Marker-based Neural Network System for Extracting Social Determinants of Healthcited by 0
  24. 2023Improving a Named Entity Recognizer Trained on Noisy Data with a Few Clean Instancescited by 0
  25. 2024A Unified Label-Aware Contrastive Learning Framework for Few-Shot Named Entity Recognitioncited by 0
  26. 2025Adversarial Demonstration Learning for Low-resource NER Using Dual Similaritycited by 0