@inproceedings{mitrofan-ion-2017-adapting,
    title = "Adapting the {TTL} {R}omanian {POS} Tagger to the Biomedical Domain",
    author = "Mitrofan, Maria  and
      Ion, Radu",
    editor = "Boytcheva, Svetla  and
      Cohen, Kevin Bretonnel  and
      Savova, Guergana  and
      Angelova, Galia",
    booktitle = "Proceedings of the Biomedical {NLP} Workshop associated with {RANLP} 2017",
    month = sep,
    year = "2017",
    address = "Varna, Bulgaria",
    publisher = "INCOMA Ltd.",
    url = "https://doi.org/10.26615/978-954-452-044-1_002",
    doi = "10.26615/978-954-452-044-1_002",
    pages = "8--14",
    abstract = "This paper presents the adaptation of the Hidden Markov Models-based TTL part-of-speech tagger to the biomedical domain. TTL is a text processing platform that performs sentence splitting, tokenization, POS tagging, chunking and Named Entity Recognition (NER) for a number of languages, including Romanian. The POS tagging accuracy obtained by the TTL POS tagger exceeds 97{\%} when TTL{'}s baseline model is updated with training information from a Romanian biomedical corpus. This corpus is developed in the context of the CoRoLa (a reference corpus for the contemporary Romanian language) project. Informative description and statistics of the Romanian biomedical corpus are also provided.",
}