mlsanityData to 7 Oct 2026

Few-shot Text Classification with Distributional Signatures

arXiv 1908.06039 ↗First posted 16 Aug 2019cs.CL cs.LGcited by 58

Not on the map. Why?

Abstract (arXiv)

In this paper, we explore meta-learning for few-shot text classification. Meta-learning has shown strong performance in computer vision, where low-level patterns are transferable across learning tasks. However, directly applying this approach to text is challenging--lexical features highly informative for one task may be insignificant for another. Thus, rather than learning solely from words, our model also leverages their distributional signatures, which encode pertinent word occurrence patterns. Our model is trained within a meta-learning framework to map these signatures into attention scores, which are then used to weight the lexical representations of words. We demonstrate that our model consistently outperforms prototypical networks learned on lexical knowledge (Snell et al., 2017) in both few-shot text classification and relation classification by a significant margin across six benchmark datasets (20.0% on average in 1-shot classification).

Key facts. Cited by 58 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 Aug 2019.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 19; 2022: 17; 2023: 15; 2024: 5; 2025: 2.

58 papers.

Sort:

By area:

  1. 2023AugGPT: Leveraging ChatGPT for Text Data Augmentationcited by 128
  2. 2021Differentiable Prompt Makes Pre-trained Language Models Better Few-shot Learnerscited by 115
  3. 2021FLEX: Unifying Evaluation for Few-Shot NLPcited by 67
  4. 2021CONTaiNER: Few-Shot Named Entity Recognition via Contrastive Learningcited by 64
  5. 2021Few-shot Conformal Prediction with Auxiliary Taskscited by 53
  6. 2021Meta-Learning with Fewer Tasks through Task Interpolationcited by 45
  7. 2024A Survey on Data Augmentation in Large Model Eracited by 31
  8. 2021Revisiting Few-shot Relation Classification: Evaluation Data and Classification Schemescited by 27
  9. 2021Revisiting Self-Training for Few-Shot Learning of Language Modelcited by 22
  10. 2022Label Semantics for Few Shot Named Entity Recognitioncited by 21
  11. 2023Unified Low-Resource Sequence Labeling by Sample-Aware Dynamic Sparse Finetuningcited by 21
  12. 2022MetaPrompting: Learning to Learn Better Promptscited by 19
38 more
  1. 2021Meta-Learning Adversarial Domain Adaptation Network for Few-Shot Text Classificationcited by 18
  2. 2022Few-shot Named Entity Recognition with Entity-level Prototypical Network Enhanced by Dispersedly Distributed Prototypescited by 17
  3. 2023ContrastNet: A Contrastive Learning Framework for Few-Shot Text Classificationcited by 17
  4. 2021Squeezing Backbone Feature Distributions to the Max for Efficient Few-Shot Learningcited by 14
  5. 2023Effective Structured Prompting by Meta-Learning and Representative Verbalizercited by 14
  6. 2022Semantic-aligned Fusion Transformer for One-shot Object Detectioncited by 13
  7. 2021Facilitating Knowledge Sharing from Domain Experts to Data Scientists for Building NLP Modelscited by 12
  8. 2022Prompt-Based Metric Learning for Few-Shot NERcited by 12
  9. 2022TAPE: Assessing Few-shot Russian Language Understandingcited by 11
  10. 2023Model-Agnostic Meta-Learning for Multilingual Hate Speech Detectioncited by 11
  11. 2021Knowledge-Aware Meta-learning for Low-Resource Text Classificationcited by 10
  12. 2021Few-Shot Emotion Recognition in Conversation with Sequential Prototypical Networkscited by 10
  13. 2021An Explicit-Joint and Supervised-Contrastive Learning Framework for Few-Shot Intent Classification and Slot Fillingcited by 9
  14. 2022Provable Generalization of Overparameterized Meta-learning Trained with SGDcited by 9
  15. 2021ProtoTransformer: A Meta-Learning Approach to Providing Student Feedbackcited by 8
  16. 2022Grad2Task: Improved Few-shot Text Classification Using Gradients for Task Representationcited by 8
  17. 2022Label Anchored Contrastive Learning for Language Understandingcited by 7
  18. 2022Label-enhanced Prototypical Network with Contrastive Learning for Multi-label Few-shot Aspect Category Detectioncited by 7
  19. 2023MetaTroll: Few-shot Detection of State-Sponsored Trolls with Transformer Adapterscited by 7
  20. 2023CPL-NoViD: Context-Aware Prompt-based Learning for Norm Violation Detection in Online Communitiescited by 7
  21. 2021Learning to Bridge Metric Spaces: Few-shot Joint Learning of Intent Detection and Slot Fillingcited by 6
  22. 2021Learning Stable Classifiers by Transferring Unstable Featurescited by 6
  23. 2022A Simple Meta-learning Paradigm for Zero-shot Intent Classification with Mixture Attention Mechanismcited by 6
  24. 2022Function-words Enhanced Attention Networks for Few-Shot Inverse Relation Classificationcited by 5
  25. 2023ICL Markup: Structuring In-Context Learning using Soft-Token Tagscited by 5
  26. 2025Dual-level Mixup for Graph Few-shot Learning with Fewer Taskscited by 5
  27. 2021ProtoInfoMax: Prototypical Networks with Mutual Information Maximization for Out-of-Domain Detectioncited by 4
  28. 2023Boosting Few-Shot Text Classification via Distribution Estimationcited by 4
  29. 2021Few-Sample Named Entity Recognition for Security Vulnerability Reports by Fine-Tuning Pre-Trained Language Modelscited by 3
  30. 2022Adaptive Meta-learner via Gradient Similarity for Few-shot Text Classificationcited by 3
  31. 2023TART: Improved Few-shot Text Classification Using Task-Adaptive Reference Transformationcited by 3
  32. 2022Disentangling Task Relations for Few-shot Text Classification via Self-Supervised Hierarchical Task Clusteringcited by 2
  33. 2023Meta-training with Demonstration Retrieval for Efficient Few-shot Learningcited by 2
  34. 2023Retrieval-Augmented Meta Learning for Low-Resource Text Classificationcited by 2
  35. 2022MGIMN: Multi-Grained Interactive Matching Network for Few-shot Text Classificationcited by 1
  36. 2022Reconciliation of Pre-trained Models and Prototypical Neural Networks in Few-shot Named Entity Recognitioncited by 1
  37. 2023Low-Resource Multi-Granularity Academic Function Recognition Based on Multiple Prompt Knowledgecited by 1
  38. 2023A Soft Contrastive Learning-based Prompt Model for Few-shot Sentiment Analysiscited by 1

50 most cited of 58 All 58 (JSON)