Zero-Shot Classification — Text Classification Without Training Data
Zero-Shot Text Classification · Also known as: zero-shot text classification, entailment-based classification, Sıfır Atışlı Sınıflandırma (Zero-Shot Classification)
Zero-shot classification is a natural-language-processing task that assigns text to categories described in plain language without requiring any labelled training data. Formalised as an entailment problem by Yin, Hay and Roth (2019), it lets a large pretrained language model recognise new categories on the fly simply by naming them, enabling rapid adaptation to fresh label sets.
Read the full method
Sign in with a free account to read this section.
Method map
The neighbourhood of related methods — select a node to explore.
When to use it
Zero-shot classification fits when you have text to categorise but no labelled training data, and when the categories may change or grow over time. It requires a large pretrained language model (such as BART or RoBERTa-based entailment models) and candidate labels that are defined clearly and disjointly. It is well suited to rapid prototyping and to settings where collecting labelled examples for every class is impractical.
Strengths & limitations
- Requires no labelled training data — categories are described in plain language.
- Adapts rapidly to new categories: adding a class only means adding its name to the candidate-label list.
- Leverages the broad linguistic knowledge already captured in a large pretrained model.
- Depends on a large pretrained language model (BART, RoBERTa), which carries computational cost.
- Accuracy hinges on how clearly and disjointly the candidate labels are worded.
- Without task-specific training it can be outperformed by a supervised classifier when ample labelled data exists.
Frequently asked
Does zero-shot classification need any training data?
No. That is its defining feature: you describe the categories as natural-language candidate labels and a large pretrained model judges the fit, so no labelled examples are required.
Which model does it rely on?
It relies on a large pretrained language model, typically an entailment-trained model such as BART or RoBERTa. The quality of the result depends heavily on using a capable pretrained model rather than a small generic one.
How should I write the candidate labels?
Define them clearly and keep them disjoint. The model compares the text against each label as written, so vague or overlapping labels blur the decision and lower accuracy.
Is it as accurate as a supervised classifier?
Not necessarily. When you have ample labelled data, a supervised classifier trained on that data can outperform zero-shot. Zero-shot shines when labelled data is scarce or the category set keeps changing.
Sources
- Yin, W., Hay, J. & Roth, D. (2019). Benchmarking Zero-shot Text Classification: Datasets, Evaluation and Entailment Approach. EMNLP, 3914-3923. DOI: 10.18653/v1/D19-1404 ↗
- Brown, T. et al. (2020). Language Models are Few-Shot Learners. NeurIPS. link ↗
How to cite this page
ScholarGate. (2026, June 1). Zero-Shot Text Classification. ScholarGate. https://scholargate.app/en/text-mining/zero-shot-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.
- Few-Shot Text ClassificationText mining↔ compare
- Sentiment AnalysisText mining↔ compare
- Text ClassificationText mining↔ compare