mlsanityData to 7 Oct 2026

FewRel 2.0: Towards More Challenging Few-Shot Relation Classification

arXiv 1910.07124 ↗First posted 16 Oct 2019cs.CLcited by 94

Not on the map. Why?

Abstract (arXiv)

We present FewRel 2.0, a more challenging task to investigate two aspects of few-shot relation classification models: (1) Can they adapt to a new domain with only a handful of instances? (2) Can they detect none-of-the-above (NOTA) relations? To construct FewRel 2.0, we build upon the FewRel dataset (Han et al., 2018) by adding a new test set in a quite different domain, and a NOTA relation choice. With the new dataset and extensive experimental analysis, we found (1) that the state-of-the-art few-shot relation classification models struggle on these two aspects, and (2) that the commonly-used techniques for domain adaptation and NOTA detection still cannot handle the two challenges well. Our research calls for more attention and further efforts to these two real-world issues. All details and resources about the dataset and baselines are released at https: //github.com/thunlp/fewrel.

Key facts. Cited by 94 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 Oct 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 24; 2022: 32; 2023: 22; 2024: 10; 2025: 5; 2026: 1.

94 papers.

Sort:

By area:

  1. 2024On LLMs-Driven Synthetic Data Generation, Curation, and Evaluation: A Surveycited by 240
  2. 2021Structured Prediction as Translation between Augmented Natural Languagescited by 183
  3. 2021CrossFit: A Few-shot Learning Challenge for Cross-task Generalization in NLPcited by 142
  4. 2023Synthetic Data Generation with Large Language Models for Text Classification: Potential and Limitationscited by 96
  5. 2023ClusterLLM: Large Language Models as a Guide for Text Clusteringcited by 69
  6. 2022Revisiting DocRED -- Addressing the False Negative Problem in Relation Extractioncited by 57
  7. 2021Neural Data Augmentation via Example Extrapolationcited by 54
  8. 2023FlexKBQA: A Flexible LLM-Powered Framework for Few-Shot Knowledge Base Question Answeringcited by 51
  9. 2023Text2KGBench: A Benchmark for Ontology-Driven Knowledge Graph Generation from Textcited by 48
  10. 2021ZS-BERT: Towards Zero-Shot Relation Extraction with Attribute Representation Learningcited by 46
  11. 2022DeepStruct: Pretraining of Language Models for Structure Predictioncited by 45
  12. 2023Aligning Instruction Tasks Unlocks Large Language Models as Zero-Shot Relation Extractorscited by 44
38 more
  1. 2023When does In-context Learning Fall Short and Why? A Study on Specification-Heavy Taskscited by 37
  2. 2021Prototypical Representation Learning for Relation Extractioncited by 33
  3. 2022Fixing Model Bugs with Natural Language Patchescited by 32
  4. 2021Revisiting Few-shot Relation Classification: Evaluation Data and Classification Schemescited by 27
  5. 2022Meta Learning for Natural Language Processing: A Surveycited by 26
  6. 2021Exploring Task Difficulty for Few-Shot Relation Extractioncited by 24
  7. 2021Zero-Shot Information Extraction as a Unified Text-to-Triple Translationcited by 22
  8. 2023A Comprehensive Survey on Relation Extraction: Recent Advances and New Frontierscited by 21
  9. 2023Unified Low-Resource Sequence Labeling by Sample-Aware Dynamic Sparse Finetuningcited by 21
  10. 2022CrossRE: A Cross-Domain Dataset for Relation Extractioncited by 20
  11. 2022What do You Mean by Relation Extraction? A Survey on Datasets and Study on Scientific Relation Classificationcited by 17
  12. 2021MapRE: An Effective Semantic Mapping Approach for Low-resource Relation Extractioncited by 16
  13. 2023A Survey of Imbalanced Learning on Graphs: Problems, Techniques, and Future Directionscited by 15
  14. 2021Entity Concept-enhanced Few-shot Relation Extractioncited by 14
  15. 2022UniRel: Unified Representation and Interaction for Joint Relational Triple Extractioncited by 14
  16. 2021Deep Neural Approaches to Relation Triplets Extraction: A Comprehensive Surveycited by 12
  17. 2022Few-shot learning for medical text: A systematic reviewcited by 12
  18. 2021Deep Neural Network Based Relation Extraction: An Overviewcited by 11
  19. 2022Few-Shot Document-Level Relation Extractioncited by 11
  20. 2025GLiREL -- Generalist Model for Zero-Shot Relation Extractioncited by 11
  21. 2021X-METRA-ADA: Cross-lingual Meta-Transfer Learning Adaptation to Natural Language Understanding and Question Answeringcited by 10
  22. 2021What Can Knowledge Bring to Machine Learning? -- A Survey of Low-shot Learning for Structured Datacited by 10
  23. 2021Knowledge-Aware Meta-learning for Low-Resource Text Classificationcited by 10
  24. 2021Diverse Distributions of Self-Supervised Tasks for Meta-Learning in NLPcited by 10
  25. 2022Information Extraction in Low-Resource Scenarios: Survey and Perspectivecited by 10
  26. 2022Active Relation Discovery: Towards General and Label-aware Open Relation Extractioncited by 10
  27. 2021Distantly-Supervised Long-Tailed Relation Extraction Using Constraint Graphscited by 9
  28. 2022A Distant Supervision Corpus for Extracting Biomedical Relationships Between Chemicals, Diseases and Genescited by 9
  29. 2022A Simple yet Effective Relation Information Guided Approach for Few-Shot Relation Extractioncited by 9
  30. 2022Pre-training to Match for Unified Low-shot Relation Extractioncited by 8
  31. 2022Better Few-Shot Relation Extraction with Label Prompt Dropoutcited by 8
  32. 2024GLiNER multi-task: Generalist Lightweight Model for Various Information Extraction Taskscited by 8
  33. 2022Label-enhanced Prototypical Network with Contrastive Learning for Multi-label Few-shot Aspect Category Detectioncited by 7
  34. 2021Learning to Bridge Metric Spaces: Few-shot Joint Learning of Intent Detection and Slot Fillingcited by 6
  35. 2023Serial Contrastive Knowledge Distillation for Continual Few-shot Relation Extractioncited by 6
  36. 2023Plug-and-Play Knowledge Injection for Pre-trained Language Modelscited by 6
  37. 2024Best of Both Worlds: A Pliable and Generalizable Neuro-Symbolic Approach for Relation Classificationcited by 6
  38. 2022A Simple but Effective Pluggable Entity Lookup Table for Pre-trained Language Modelscited by 5

50 most cited of 94 All 94 (JSON)