mlsanityData to 7 Oct 2026

A Closer Look At Feature Space Data Augmentation For Few-Shot Intent Classification

arXiv 1910.04176 ↗First posted 9 Oct 2019cs.CL cs.IR cs.LGcited by 45

Not on the map. Why?

Abstract (arXiv)

New conversation topics and functionalities are constantly being added to conversational AI agents like Amazon Alexa and Apple Siri. As data collection and annotation is not scalable and is often costly, only a handful of examples for the new functionalities are available, which results in poor generalization performance. We formulate it as a Few-Shot Integration (FSI) problem where a few examples are used to introduce a new intent. In this paper, we study six feature space data augmentation methods to improve classification performance in FSI setting in combination with both supervised and unsupervised representation learning methods such as BERT. Through realistic experiments on two public conversational datasets, SNIPS, and the Facebook Dialog corpus, we show that data augmentation in feature space provides an effective way to improve intent classification performance in few-shot setting beyond traditional transfer learning approaches. In particular, we show that (a) upsampling in latent space is a competitive baseline for feature space augmentation (b) adding the difference between two examples to a new example is a simple yet effective data augmentation method.

Key facts. Cited by 45 papers in the map (data through 7 Oct 2026). First posted on arXiv 9 Oct 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 11; 2022: 16; 2023: 10; 2024: 5; 2025: 2; 2026: 1.

45 papers.

Sort:

By area:

  1. 2021A Survey of Data Augmentation Approaches for NLPcited by 408
  2. 2023AugGPT: Leveraging ChatGPT for Text Data Augmentationcited by 128
  3. 2021A Survey on Data Augmentation for Text Classificationcited by 111
  4. 2021Neural Data Augmentation via Example Extrapolationcited by 54
  5. 2022Data Augmentation for Intent Classification with Off-the-shelf Large Language Modelscited by 49
  6. 2021Controllable Semantic Parsing via Retrieval Augmentationcited by 35
  7. 2022SgVA-CLIP: Semantic-guided Visual Adapting of Vision-Language Models for Few-shot Image Classificationcited by 34
  8. 2021FlipDA: Effective and Robust Data Augmentation for Few-Shot Learningcited by 32
  9. 2023Mask-guided BERT for Few Shot Text Classificationcited by 25
  10. 2023PromptMix: A Class Boundary Augmentation Method for Large Language Model Distillationcited by 25
  11. 2023Selective In-Context Data Augmentation for Intent Detection using Pointwise V-Informationcited by 24
  12. 2023Using GPT-4 to Augment Unbalanced Data for Automatic Scoringcited by 20
33 more
  1. 2022Contrastive Learning for Prompt-Based Few-Shot Language Learnerscited by 17
  2. 2022Learning Multimodal Data Augmentation in Feature Spacecited by 17
  3. 2022Data Augmentation with Paraphrase Generation and Entity Extraction for Multimodal Dialogue Systemcited by 16
  4. 2023Hallucination Improves the Performance of Unsupervised Visual Representation Learningcited by 16
  5. 2021Coarse2Fine: Fine-grained Text Classification on Coarsely-grained Annotated Datacited by 13
  6. 2022Opponent Modeling in Negotiation Dialogues by Related Data Adaptationcited by 13
  7. 2022A Feature-space Multimodal Data Augmentation Technique for Text-video Retrievalcited by 13
  8. 2024Frozen Feature Augmentation for Few-Shot Image Classificationcited by 13
  9. 2021ECKPN: Explicit Class Knowledge Propagation Network for Transductive Few-shot Learningcited by 11
  10. 2023PAC-tuning:Fine-tuning Pretrained Language Models with PAC-driven Perturbed Gradient Descentcited by 10
  11. 2024mCSQA: Multilingual Commonsense Reasoning Dataset with Unified Creation Strategy by Language Models and Humanscited by 10
  12. 2021ProtoDA: Efficient Transfer Learning for Few-Shot Intent Classificationcited by 8
  13. 2024Exploring Empty Spaces: Human-in-the-Loop Data Augmentationcited by 6
  14. 2021Good-Enough Example Extrapolationcited by 5
  15. 2022Embedding Hallucination for Few-Shot Language Fine-tuningcited by 5
  16. 2022AugCSE: Contrastive Sentence Embedding with Diverse Augmentationscited by 5
  17. 2022CST5: Data Augmentation for Code-Switched Semantic Parsingcited by 5
  18. 2023Boosting Few-Shot Text Classification via Distribution Estimationcited by 4
  19. 2023Improving Few-shot Generalization of Safety Classifiers via Data Augmented Parameter-Efficient Fine-Tuningcited by 4
  20. 2024What Has Been Overlooked in Contrastive Source-Free Domain Adaptation: Leveraging Source-Informed Latent Augmentation within Neighborhood Contextcited by 4
  21. 2022UpCycling: Semi-supervised 3D Object Detection without Sharing Raw-level Unlabeled Scenescited by 3
  22. 2023From Chatter to Matter: Addressing Critical Steps of Emotion Recognition Learning in Task-oriented Dialoguecited by 3
  23. 2022Multi-Granularity Cross-Modality Representation Learning for Named Entity Recognition on Social Mediacited by 2
  24. 2021Meta-learning for skin cancer detection using Deep Learning Techniquescited by 1
  25. 2021ALLWAS: Active Learning on Language models in WASserstein spacecited by 1
  26. 2022Variational Autoencoder with Disentanglement Priors for Low-Resource Task-Specific Natural Language Generationcited by 1
  27. 2022Reprint: a randomized extrapolation based on principal components for data augmentationcited by 1
  28. 2022Multi-features based Semantic Augmentation Networks for Named Entity Recognition in Threat Intelligencecited by 1
  29. 2025SiameseDuo++: Active Learning from Data Streams with Dual Augmented Siamese Networkscited by 1
  30. 2022Progressive Feature Upgrade in Semi-supervised Learning on Tabular Domaincited by 0
  31. 2024Feature Augmentation for Self-supervised Contrastive Learning: A Closer Lookcited by 0
  32. 2025A Comprehensive Survey of Challenges and Opportunities of Few-Shot Learning Across Multiple Domainscited by 0
  33. 2026Semantics-Aware Generative Latent Data Augmentation for Learning in Low-Resource Domainscited by 0