{
 "id": "SEACrowd/ara_close",
 "owner": "SEACrowd",
 "name": "ara_close",
 "downloads": 72,
 "likes": 0,
 "last_modified": "2024-06-24T13:25:26.000Z",
 "stated_licence": "cc-by-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": "cc-by-4.0",
 "licence_files": [
  "LICENSE"
 ],
 "sources": [],
 "gated": false,
 "tasks": [
  "readability-assessment"
 ],
 "citation": "@inproceedings{imperial-kochmar-2023-automatic,\n    title = \"Automatic Readability Assessment for Closely Related Languages\",\n    author = \"Imperial, Joseph Marvin  and\n      Kochmar, Ekaterina\",\n    editor = \"Rogers, Anna  and\n      Boyd-Graber, Jordan  and\n      Okazaki, Naoaki\",\n    booktitle = \"Findings of the Association for Computational Linguistics: ACL 2023\",\n    month = jul,\n    year = \"2023\",\n    address = \"Toronto, Canada\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2023.findings-acl.331\",\n    doi = \"10.18653/v1/2023.findings-acl.331\",\n    pages = \"5371--5386\",\n    abstract = \"In recent years, the main focus of research on automatic readability assessment (ARA)     has shifted towards using expensive deep learning-based methods with the primary goal of increasing models{'} accuracy.     This, however, is rarely applicable for low-resource languages where traditional handcrafted features are still     widely used due to the lack of existing NLP tools to extract deeper linguistic representations. In this work,     we take a step back from the technical component and focus on how linguistic aspects such as mutual intelligibility     or degree of language relatedness can improve ARA in a low-resource setting. We collect short stories written in three     languages in the Philippines{---}Tagalog, Bikol, and Cebuano{---}to train readability assessment models and explore the     interaction of data and features in vari",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-4.0) is classified as permissive.",
 "revision": "b7fb62b4e2c50f3849956d5fcdaa989fe4dc040a",
 "stated_evidence": "https://huggingface.co/datasets/SEACrowd/ara_close/blob/b7fb62b4e2c50f3849956d5fcdaa989fe4dc040a/README.md",
 "file_evidence": "https://huggingface.co/datasets/SEACrowd/ara_close/blob/b7fb62b4e2c50f3849956d5fcdaa989fe4dc040a/LICENSE",
 "card_nc": false
}