@inproceedings{scherrer-ljubesic-2021-sesame,
    title = "Sesame Street to Mount Sinai: {BERT}-constrained character-level {M}oses models for multilingual lexical normalization",
    author = "Scherrer, Yves  and
      Ljube{\v{s}}i{\'c}, Nikola",
    editor = "Xu, Wei  and
      Ritter, Alan  and
      Baldwin, Tim  and
      Rahimi, Afshin",
    booktitle = "Proceedings of the Seventh Workshop on Noisy User-generated Text (W-NUT 2021)",
    month = nov,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2021.wnut-1.52/",
    doi = "10.18653/v1/2021.wnut-1.52",
    pages = "465--472",
    abstract = "This paper describes the HEL-LJU submissions to the MultiLexNorm shared task on multilingual lexical normalization. Our system is based on a BERT token classification preprocessing step, where for each token the type of the necessary transformation is predicted (none, uppercase, lowercase, capitalize, modify), and a character-level SMT step where the text is translated from original to normalized given the BERT-predicted transformation constraints. For some languages, depending on the results on development data, the training data was extended by back-translating OpenSubtitles data. In the final ordering of the ten participating teams, the HEL-LJU team has taken the second place, scoring better than the previous state-of-the-art."
}