@inproceedings{pinnis-2018-tildes,
    title = "Tilde`s Parallel Corpus Filtering Methods for {WMT} 2018",
    author = "Pinnis, M{\={a}}rcis",
    editor = "Bojar, Ond{\v{r}}ej  and
      Chatterjee, Rajen  and
      Federmann, Christian  and
      Fishel, Mark  and
      Graham, Yvette  and
      Haddow, Barry  and
      Huck, Matthias  and
      Yepes, Antonio Jimeno  and
      Koehn, Philipp  and
      Monz, Christof  and
      Negri, Matteo  and
      N{\'e}v{\'e}ol, Aur{\'e}lie  and
      Neves, Mariana  and
      Post, Matt  and
      Specia, Lucia  and
      Turchi, Marco  and
      Verspoor, Karin",
    booktitle = "Proceedings of the Third Conference on Machine Translation: Shared Task Papers",
    month = oct,
    year = "2018",
    address = "Belgium, Brussels",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/W18-6486/",
    doi = "10.18653/v1/W18-6486",
    pages = "939--945",
    abstract = "The paper describes parallel corpus filtering methods that allow reducing noise of noisy {\textquotedblleft}parallel{\textquotedblright} corpora from a level where the corpora are not usable for neural machine translation training (i.e., the resulting systems fail to achieve reasonable translation quality; well below 10 BLEU points) up to a level where the trained systems show decent (over 20 BLEU points on a 10 million word dataset and up to 30 BLEU points on a 100 million word dataset). The paper also documents Tilde`s submissions to the WMT 2018 shared task on parallel corpus filtering."
}