Skip to contentScholarGate
LibraryBookshelfDeskReview StudioAssistant
Sign in
On this page
IntuitionHow it worksWhen to use itStrengths & limitationsCommon pitfallsApplicationsFrequently asked🔒 Read the full methodSourcesRelated methods
Cite this pageSpotted an issue on this page? Report or suggest a fix →
Home›Text mining›Few-Shot Text Classification
Process / pipeline

Few-Shot Text Classification

Also known as: few-shot learning for text, Az Atışlı Metin Sınıflandırma (Few-Shot)

Few-shot text classification assigns documents to classes using only a handful of labelled examples per class. Building on advances by Gao et al. (2021) and the prompt-free SetFit approach of Tunstall et al. (2022), it leans on prototypical networks, MAML, or fine-tuning of a large pretrained model to learn from scarce labels.

ScholarGate
  1. Process / pipeline
  2. v1
  3. 2 Sources
  4. PUBLISHED
Cite this page →
Tools & resources
Download slides
Learn & explore

Read the full method

Members only

Sign in with a free account to read this section.

Sign in

Method map

The neighbourhood of related methods — select a node to explore.

Few-Shot Text Classification
BERT EmbeddingsDomain AdaptationSentiment AnalysisText ClassificationPrompt EngineeringZero-Shot Classification

When to use it

Use few-shot text classification when you have text to classify but only a few labelled examples per class — far fewer than a conventional supervised classifier would need. It assumes at least one example exists for every class and works best when a large pretrained model is available to supply the missing knowledge. With abundant labelled data, an ordinary supervised text classifier is the simpler choice.

Strengths & limitations

Strengths
  • Learns from very few labelled examples — as little as one per class — where conventional supervised classifiers fail.
  • Reuses the broad language knowledge inside a large pretrained model, so little task-specific data is needed.
  • Flexible across strategies: prototypical networks, MAML, or lightweight fine-tuning all fit the same pipeline.
Limitations
  • Needs at least one labelled example for every class; entirely unseen classes cannot be predicted.
  • Quality depends heavily on the pretrained backbone — a weak or mismatched model limits performance.
  • With extremely few examples, predictions can be unstable and sensitive to which examples were chosen.

Frequently asked

How few examples per class does it really need?

At least one labelled example per class is required, and the method is designed to work with only a few per class. The fewer you provide, the more it leans on the pretrained backbone's prior knowledge.

Which few-shot strategy should I use?

Prototypical networks build a prototype per class from the few examples and classify by nearest prototype; MAML meta-learns parameters that adapt quickly to new tasks; fine-tuning lightly updates a pretrained model on the small set. All three fit the same pipeline; the prompt-free SetFit style of fine-tuning is a practical default.

Why does the pretrained model matter so much?

With only a few labelled examples, most of the knowledge has to come from somewhere else. A large pretrained model supplies broad language understanding, so a stronger backbone generally gives better few-shot results.

When should I prefer a normal supervised classifier instead?

When you have abundant labelled data. Few-shot methods exist for the low-label regime; with a large balanced labelled set, a standard supervised text classifier is simpler and usually stronger.

Sources

  1. Gao, T., Fisch, A. & Chen, D. (2021). Making Pre-trained Language Models Better Few-shot Learners. ACL. DOI: 10.18653/v1/2021.acl-long.295 ↗
  2. Tunstall, L., Reimers, N., Jo, U.E.S., Bates, L., Korat, D., Wasserblat, M. & Pereg, O. (2022). Efficient Few-Shot Learning Without Prompts. arXiv. DOI: 10.48550/arXiv.2209.11055 ↗

How to cite this page

ScholarGate. (2026, June 1). Few-Shot Text Classification. ScholarGate. https://scholargate.app/en/text-mining/few-shot-text-classification

Related methods

BERT EmbeddingsDomain AdaptationSentiment AnalysisText Classification

Which method?

Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.

  • BERT EmbeddingsText mining↔ compare
  • Domain AdaptationText mining↔ compare
  • Sentiment AnalysisText mining↔ compare
  • Text ClassificationText mining↔ compare
Compare side by side →

Referenced by

Prompt EngineeringZero-Shot Classification

Similar methods

Few-shot LearningZero-Shot ClassificationText ClassificationOnline Few-shot LearningSemi-supervised Few-shot LearningBayesian Few-Shot LearningSelf-supervised Few-shot LearningRegularized Few-Shot Learning

Related reference concepts

Text ClassificationText Classification and Sentiment AnalysisText ClusteringText Representation and ClassificationClassification AlgorithmsLearning to Rank

Spotted an issue on this page? Report or suggest a fix →

ScholarGate — Few-Shot Text Classification (Few-Shot Text Classification). Retrieved 2026-07-21 from https://scholargate.app/en/text-mining/few-shot-text-classification · Dataset: https://doi.org/10.5281/zenodo.20539026
Quick facts
Type
NLP text-classification task (low-resource)
Approaches
Prototypical networks / MAML / pretrained-model fine-tuning
MinLabelsPerClass
As few as 1 example per class
Output
Class label per document
Related methods
BERT EmbeddingsDomain AdaptationSentiment AnalysisText Classification
ScholarGate

A content-first reference library for research methods — what each one is, how it works, and where it comes from.

Open data (CC-BY)

Explore

  • Library
  • Search the library…
  • Browse by field
  • Fields
  • Journey
  • Compare
  • Which method?

Reference

  • Subjects
  • Atlas
  • Glossary
  • Methodology
  • Philosophy

Your tools

  • Bookshelf
  • Desk
  • Chat

Company

  • About
  • Pricing
  • Contact
  • Suggest a method

Entries are compiled from published sources for reference. Verifying the accuracy and suitability of any information for your own use remains your responsibility.

© 2026 ScholarGate · A research-method reference library
  • Privacy
  • Cookies
  • Terms
  • Delete account