@inproceedings{fonseca-etal-2019-findings,
    title = "Findings of the {WMT} 2019 Shared Tasks on Quality Estimation",
    author = "Fonseca, Erick  and
      Yankovskaya, Lisa  and
      Martins, Andr{\'e} F. T.  and
      Fishel, Mark  and
      Federmann, Christian",
    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
      Martins, Andr{\'e}  and
      Monz, Christof  and
      Negri, Matteo  and
      N{\'e}v{\'e}ol, Aur{\'e}lie  and
      Neves, Mariana  and
      Post, Matt  and
      Turchi, Marco  and
      Verspoor, Karin",
    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/W19-5401",
    doi = "10.18653/v1/W19-5401",
    pages = "1--10",
    abstract = "We report the results of the WMT19 shared task on Quality Estimation, i.e. the task of predicting the quality of the output of machine translation systems given just the source text and the hypothesis translations. The task includes estimation at three granularity levels: word, sentence and document. A novel addition is evaluating sentence-level QE against human judgments: in other words, designing MT metrics that do not need a reference translation. This year we include three language pairs, produced solely by neural machine translation systems. Participating teams from eleven institutions submitted a variety of systems to different task variants and language pairs.",
}