{
 "id": "impresso-project/sts-h-paraphrase-detection",
 "owner": "impresso-project",
 "name": "sts-h-paraphrase-detection",
 "downloads": 35,
 "likes": 0,
 "last_modified": "2025-01-30T16:31:45.000Z",
 "stated_licence": "apache-2.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-classification"
 ],
 "citation": "If you use this dataset, please cite it using the following BibTeX entry:\n\n```bibtex\n@inproceedings{michail-etal-2025-paraphrasus,\n    title = \"{PARAPHRASUS}: A Comprehensive Benchmark for Evaluating Paraphrase Detection Models\",\n    author = \"Michail, Andrianos  and\n      Clematide, Simon  and\n      Opitz, Juri\",\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.585/\",\n    pages = \"8749--8762\",\n    abstract = \"The task of determining whether two texts are paraphrases has long been a challenge in NLP. However, the prevailing notion of paraphrase is often quite simplistic, offering only a limited view of the vast spectrum of paraphrase phenomena. Indeed, we find that evaluating models in a paraphrase dataset can leave uncertainty about their true semantic understanding. To alleviate this, we create PARAPHRASUS, a benchmark designed for multi-dimensional assessment, benchmarking and selection of paraphrase detection models. We find that paraphrase detection models under our fine-grained evaluation lens exhibit trade-offs that cannot be captured through a single classification dataset",
 "signal": "permissive",
 "reason": "The declared licence (apache-2.0) is classified as permissive.",
 "revision": "0b7653736215f1da30a59bbebd06754d37d31be4",
 "stated_evidence": "https://huggingface.co/datasets/impresso-project/sts-h-paraphrase-detection/blob/0b7653736215f1da30a59bbebd06754d37d31be4/README.md",
 "file_evidence": "https://huggingface.co/datasets/impresso-project/sts-h-paraphrase-detection/tree/0b7653736215f1da30a59bbebd06754d37d31be4",
 "card_nc": false
}