{
 "id": "catherinearnett/morphscore",
 "owner": "catherinearnett",
 "name": "morphscore",
 "downloads": 614,
 "likes": 4,
 "last_modified": "2025-07-10T15:50:17.000Z",
 "stated_licence": "cc-by-sa-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [],
 "citation": "@inproceedings{arnett2025alignment,\n  author = {Arnett, Catherine and Hudspeth, Marisa and O'Connor, Brendan},\n  title = {{Evaluating Morphological Alignment of Tokenizers in 70 Languages}},\n  year = {2025},\n  booktitle={Proceedings of the ICML 2025 Tokenization Workshop (TokShop)},\n  url = {https://arxiv.org/abs/2507.06378}\n}\n\n\n@inproceedings{arnett-bergen-2025-language,\n    title = \"Why do language models perform worse for morphologically complex languages?\",\n    author = \"Arnett, Catherine  and\n      Bergen, Benjamin\",\n    editor = \"Rambow, Owen  and\n      Wanner, Leo  and\n      Apidianaki, Marianna  and\n      Al-Khalifa, Hend  and\n      Eugenio, Barbara Di  and\n      Schockaert, Steven\",\n    booktitle = \"Proceedings of the 31st International Conference on Computational Linguistics\",\n    month = jan,\n    year = \"2025\",\n    address = \"Abu Dhabi, UAE\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2025.coling-main.441/\",\n    pages = \"6607--6623\"\n}",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-sa-4.0) is classified as share-alike.",
 "revision": "bd39be59e4d17f3d324c405aeb9adc51216a52e3",
 "stated_evidence": "https://huggingface.co/datasets/catherinearnett/morphscore/blob/bd39be59e4d17f3d324c405aeb9adc51216a52e3/README.md",
 "file_evidence": "https://huggingface.co/datasets/catherinearnett/morphscore/tree/bd39be59e4d17f3d324c405aeb9adc51216a52e3",
 "card_nc": false
}