@inproceedings{colakoglu-etal-2019-normalizing,
    title = "Normalizing Non-canonical {T}urkish Texts Using Machine Translation Approaches",
    author = {{\c{C}}olako{\u{g}}lu, Talha  and
      Sulubacak, Umut  and
      Tantu{\u{g}}, Ahmet C{\"u}neyd},
    booktitle = "Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop",
    month = jul,
    year = "2019",
    address = "Florence, Italy",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/P19-2037",
    doi = "10.18653/v1/P19-2037",
    pages = "267--272",
    abstract = "With the growth of the social web, user-generated text data has reached unprecedented sizes. Non-canonical text normalization provides a way to exploit this as a practical source of training data for language processing systems. The state of the art in Turkish text normalization is composed of a token level pipeline of modules, heavily dependent on external linguistic resources and manually defined rules. Instead, we propose a fully automated, context-aware machine translation approach with fewer stages of processing. Experiments with various implementations of our approach show that we are able to surpass the current best-performing system by a large margin.",
}