small-text 1.0.0a7

A simple, modular active learning library for text classification.

Active Learning for Text Classifcation in Python.

---

Installation | Quick Start | Docs

Active Learning allows you to efficiently label training data in a small-data scenario.

This library provides state-of-the-art active learning for text classification which allows to easily mix and match many classifiers and query strategies to build active learning experiments or applications.

Features

• Provides unified interfaces for Active Learning so that you can easily use any classifier provided by sklearn.
• (Optionally) As an optional feature, you can also use pytorch classifiers, including transformer models.
• Multiple scientifically-proven strategies re-implemented: Query Strategies, Initialization Strategies

Installation

Small-text can be easily installed via pip:

pip install small-text

For a full installation include the transformers extra requirement:

pip install small-text[transformers]

Requires Python 3.7 or newer. For using the GPU, CUDA 10.1 or newer is required. More information regarding the installation can be found in the documentation.

Quick Start

For a quick start, see the provided examples for binary classification, pytorch multi-class classification, or transformer-based multi-class classification

Documentation

Read the latest documentation (currently work in progress) here.

Alternatives

• modAL
• ALiPy
• libact

Contribution

Contributions are welcome. Details can be found in CONTRIBUTING.md.

Acknowledgments

This software was created by @chschroeder at Leipzig University's NLP group which is a part of the Webis research network. The encompassing project was funded by the Development Bank of Saxony (SAB) under project number 100335729.

Citation

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

@misc{schroeder2021smalltext,
    title={Small-text: Active Learning for Text Classification in Python}, 
    author={Christopher Schröder and Lydia Müller and Andreas Niekler and Martin Potthast},
    year={2021},
    eprint={2107.10314},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}

License

MIT License