@inproceedings{koehn-etal-2019-findings,
    title = "Findings of the {WMT} 2019 Shared Task on Parallel Corpus Filtering for Low-Resource Conditions",
    author = "Koehn, Philipp  and
      Guzm{\'a}n, Francisco  and
      Chaudhary, Vishrav  and
      Pino, Juan",
    booktitle = "Proceedings of the Fourth Conference on Machine Translation (Volume 3: Shared Task Papers, Day 2)",
    month = aug,
    year = "2019",
    address = "Florence, Italy",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/W19-5404",
    doi = "10.18653/v1/W19-5404",
    pages = "54--72",
    abstract = "Following the WMT 2018 Shared Task on Parallel Corpus Filtering, we posed the challenge of assigning sentence-level quality scores for very noisy corpora of sentence pairs crawled from the web, with the goal of sub-selecting 2{\%} and 10{\%} of the highest-quality data to be used to train machine translation systems. This year, the task tackled the low resource condition of Nepali-English and Sinhala-English. Eleven participants from companies, national research labs, and universities participated in this task.",
}