@inproceedings{koksal-etal-2020-turki,
    title = "{\#}Turki{\$}h{T}weets: A Benchmark Dataset for {T}urkish Text Correction",
    author = {Koksal, Asiye Tuba  and
      Bozal, Ozge  and
      Y{\"u}rekli, Emre  and
      Gezici, Gizem},
    editor = "Cohn, Trevor  and
      He, Yulan  and
      Liu, Yang",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2020",
    month = nov,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2020.findings-emnlp.374/",
    doi = "10.18653/v1/2020.findings-emnlp.374",
    pages = "4190--4198",
    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."
}