@inproceedings{agic-vulic-2019-jw300,
    title = "{JW}300: A Wide-Coverage Parallel Corpus for Low-Resource Languages",
    author = "Agi{\'c}, {\v{Z}}eljko  and
      Vuli{\'c}, Ivan",
    editor = "Korhonen, Anna  and
      Traum, David  and
      M{\`a}rquez, Llu{\'i}s",
    booktitle = "Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics",
    month = jul,
    year = "2019",
    address = "Florence, Italy",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/P19-1310/",
    doi = "10.18653/v1/P19-1310",
    pages = "3204--3210",
    abstract = "Viable cross-lingual transfer critically depends on the availability of parallel texts. Shortage of such resources imposes a development and evaluation bottleneck in multilingual processing. We introduce JW300, a parallel corpus of over 300 languages with around 100 thousand parallel sentences per language pair on average. In this paper, we present the resource and showcase its utility in experiments with cross-lingual word embedding induction and multi-source part-of-speech projection."
}