@inproceedings{banon-etal-2020-paracrawl,
    title = "{P}ara{C}rawl: Web-Scale Acquisition of Parallel Corpora",
    author = "Ba{\~n}{\'o}n, Marta  and
      Chen, Pinzhen  and
      Haddow, Barry  and
      Heafield, Kenneth  and
      Hoang, Hieu  and
      Espl{\`a}-Gomis, Miquel  and
      Forcada, Mikel L.  and
      Kamran, Amir  and
      Kirefu, Faheem  and
      Koehn, Philipp  and
      Ortiz Rojas, Sergio  and
      Pla Sempere, Leopoldo  and
      Ram{\'\i}rez-S{\'a}nchez, Gema  and
      Sarr{\'\i}as, Elsa  and
      Strelec, Marek  and
      Thompson, Brian  and
      Waites, William  and
      Wiggins, Dion  and
      Zaragoza, Jaume",
    booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics",
    month = jul,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2020.acl-main.417",
    doi = "10.18653/v1/2020.acl-main.417",
    pages = "4555--4567",
    abstract = "We report on methods to create the largest publicly available parallel corpora by crawling the web, using open source software. We empirically compare alternative methods and publish benchmark data sets for sentence alignment and sentence pair filtering. We also describe the parallel corpora released and evaluate their quality and their usefulness to create machine translation systems.",
}