Small-Text provides active learning for text classification. It is designed to offer a robust and modular set of components for both experimental and applied active learning.

Getting Started

For now, the best way to get started is checking out the folders examples/notebooks/ and examples/examplecode/ in the github directory.

Active Learning Components

All components are based around the ActiveLearner class. You can mix and match different many initialization strategies, query strategies, and Classifiers.


Optional Integrations allow you to use models from other libraries such as pytorch or transformers.

Common Patterns

We provide patterns to common challenges when building experiments and/or applications, such as Data Management and Serialization.


A preprint which introduces small-text is available here: Small-text: Active Learning for Text Classification in Python.

    title={Small-text: Active Learning for Text Classification in Python},
    author={Christopher Schröder and Lydia Müller and Andreas Niekler and Martin Potthast},

Index | Module Index | Search Page