{"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/turki-htweets-a-benchmark-dataset-for-turkish","title":"\\#Turki\\$hTweets: A Benchmark Dataset for Turkish Text Correction","arxiv_id":null,"date":"2020-11-01","proceeding":"Findings of the Association for Computational Linguistics 2020","authors":["Asiye Tuba Koksal","Ozge Bozal","Emre Y{\\\"u}rekli","Gizem Gezici"],"abstract":"{\\#}Turki{\\$}hTweets is a benchmark dataset for the task of correcting the user misspellings, with the purpose of introducing the first public Turkish dataset in this area. {\\#}Turki{\\$}hTweets provides correct/incorrect word annotations with a detailed misspelling category formulation based on the real user data. We evaluated four state-of-the-art approaches on our dataset to present a preliminary analysis for the sake of reproducibility.","url_abs":"https://aclanthology.org/2020.findings-emnlp.374","url_pdf":"https://aclanthology.org/2020.findings-emnlp.374.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":"turki-htweets-a-benchmark-dataset-for-turkish","repo_url":"https://github.com/atubakoksal/annotated_tweets","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}