@inproceedings{koehn-etal-2018-findings,
    title = "Findings of the {WMT} 2018 Shared Task on Parallel Corpus Filtering",
    author = "Koehn, Philipp  and
      Khayrallah, Huda  and
      Heafield, Kenneth  and
      Forcada, Mikel L.",
    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://aclanthology.org/W18-6453",
    doi = "10.18653/v1/W18-6453",
    pages = "726--739",
    abstract = "We posed the shared task of assigning sentence-level quality scores for a very noisy corpus of sentence pairs crawled from the web, with the goal of sub-selecting 1{\%} and 10{\%} of high-quality data to be used to train machine translation systems. Seventeen participants from companies, national research labs, and universities participated in this task.",
}