{"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/discriminating-between-similar-nordic","title":"Discriminating Between Similar Nordic Languages","arxiv_id":"2012.06431","date":"2020-12-11","proceeding":"EACL (VarDial) 2021 4","authors":["René Haas","Leon Derczynski"],"abstract":"Automatic language identification is a challenging problem. Discriminating between closely related languages is especially difficult. This paper presents a machine learning approach for automatic language identification for the Nordic languages, which often suffer miscategorisation by existing state-of-the-art tools. Concretely we will focus on discrimination between six Nordic languages: Danish, Swedish, Norwegian (Nynorsk), Norwegian (Bokm{\\aa}l), Faroese and Icelandic.","url_abs":"https://arxiv.org/abs/2012.06431v2","url_pdf":"https://arxiv.org/pdf/2012.06431v2.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":"discriminating-between-similar-nordic","repo_url":"https://github.com/StrombergNLP/NordicDSL","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"discriminating-between-similar-nordic","repo_url":"https://github.com/renhaa/NordicDSL","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"},{"task_slug":"language-identification","task_name":"Language Identification"}],"methods":[],"datasets_introduced":[{"slug":"nordic-langid","name":"Nordic Language Identification","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/language-identification-on-nordic-langid","task":"Language Identification","dataset":"Nordic Language Identification","model":"FastText","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"0.9711"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}