{
  "id": "2107.10314",
  "version": "v1",
  "published": "2021-07-21T19:23:56.000Z",
  "updated": "2021-07-21T19:23:56.000Z",
  "title": "Small-text: Active Learning for Text Classification in Python",
  "authors": [
    "Christopher Schröder",
    "Lydia Müller",
    "Andreas Niekler",
    "Martin Potthast"
  ],
  "comment": "preprint",
  "categories": [
    "cs.LG",
    "cs.CL"
  ],
  "abstract": "We present small-text, a simple modular active learning library, which offers pool-based active learning for text classification in Python. It comes with various pre-implemented state-of-the-art query strategies, including some which can leverage the GPU. Clearly defined interfaces allow to combine a multitude of such query strategies with different classifiers, thereby facilitating a quick mix and match, and enabling a rapid development of both active learning experiments and applications. To make various classifiers accessible in a consistent way, it integrates several well-known machine learning libraries, namely, scikit-learn, PyTorch, and huggingface transformers -- for which the latter integrations are available as optionally installable extensions. The library is available under the MIT License at https://github.com/webis-de/small-text.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2021-07-21T19:23:56.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "text classification",
      "small-text",
      "pre-implemented state-of-the-art query strategies",
      "simple modular active learning library",
      "well-known machine learning libraries"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}