{
 "id": "turkish-nlp-suite/OzenliDerlem",
 "owner": "turkish-nlp-suite",
 "name": "OzenliDerlem",
 "downloads": 708,
 "likes": 11,
 "last_modified": "2026-03-07T10:40:10.000Z",
 "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{10.1007/978-3-031-70563-2_16,\nauthor=\"Altinok, Duygu\",\neditor=\"N{\\\"o}th, Elmar\nand Hor{\\'a}k, Ale{\\v{s}}\nand Sojka, Petr\",\ntitle=\"Bella Turca: A Large-Scale Dataset of Diverse Text Sources for Turkish Language Modeling\",\nbooktitle=\"Text, Speech, and Dialogue\",\nyear=\"2024\",\npublisher=\"Springer Nature Switzerland\",\naddress=\"Cham\",\npages=\"196--213\",\nabstract=\"In recent studies, it has been demonstrated that incorporating diverse training datasets enhances the overall knowledge and generalization capabilities of large-scale language models, especially in cross-domain scenarios. In line with this, we introduce Bella Turca: a comprehensive Turkish text corpus, totaling 265GB, specifically curated for training language models. Bella Turca encompasses 25 distinct subsets of 4 genre, carefully chosen to ensure diversity and high quality. While Turkish is spoken widely across three continents, it suffers from a dearth of robust data resources for language modelling. Existing transformers and language models have primarily relied on repetitive corpora such as OSCAR and/or Wiki, which lack the desired diversity. Our work aims to break free from this monotony by introducing a fresh perspective to Turkish corpora resources. To the best of our knowledge, this release marks the first instance of such a vast and diverse dataset tailored for the Turkish language. Additionally, we contribute to the community by providing the code used in the dataset's construction and cleaning, f",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-sa-4.0) is classified as share-alike.",
 "revision": "539fc60c4565fc556fbb5b1dab6cb872e7fb5db6",
 "stated_evidence": "https://huggingface.co/datasets/turkish-nlp-suite/OzenliDerlem/blob/539fc60c4565fc556fbb5b1dab6cb872e7fb5db6/README.md",
 "file_evidence": "https://huggingface.co/datasets/turkish-nlp-suite/OzenliDerlem/tree/539fc60c4565fc556fbb5b1dab6cb872e7fb5db6",
 "card_nc": false
}