{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/the-wili-benchmark-dataset-for-written","title":"The WiLI benchmark dataset for written language identification","arxiv_id":"1801.07779","date":"2018-01-23","proceeding":null,"authors":["Martin Thoma"],"abstract":"This paper describes the WiLI-2018 benchmark dataset for monolingual written\nnatural language identification. WiLI-2018 is a publicly available, free of\ncharge dataset of short text extracts from Wikipedia. It contains 1000\nparagraphs of 235 languages, totaling in 23500 paragraphs. WiLI is a\nclassification dataset: Given an unknown paragraph written in one dominant\nlanguage, it has to be decided which language it is.","url_abs":"http://arxiv.org/abs/1801.07779v1","url_pdf":"http://arxiv.org/pdf/1801.07779v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"the-wili-benchmark-dataset-for-written","repo_url":"https://github.com/LauraRuis/LanguageIdentification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"the-wili-benchmark-dataset-for-written","repo_url":"https://github.com/birolkuyumcu/language_identification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"the-wili-benchmark-dataset-for-written","repo_url":"https://github.com/sergeisoly/Russian-Language-Identification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"the-wili-benchmark-dataset-for-written","repo_url":"https://github.com/tsimafeip/nn-hackathon","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"language-identification","task_name":"Language Identification"}],"methods":[],"datasets_introduced":[{"slug":"wili-2018","name":"WiLI-2018","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1801.07779","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}