@inproceedings{izbicki-2022-aligning,
    title = "Aligning Word Vectors on Low-Resource Languages with {W}iktionary",
    author = "Izbicki, Mike",
    editor = "Ojha, Atul Kr.  and
      Liu, Chao-Hong  and
      Vylomova, Ekaterina  and
      Abbott, Jade  and
      Washington, Jonathan  and
      Oco, Nathaniel  and
      Pirinen, Tommi A  and
      Malykh, Valentin  and
      Logacheva, Varvara  and
      Zhao, Xiaobing",
    booktitle = "Proceedings of the Fifth Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2022)",
    month = oct,
    year = "2022",
    address = "Gyeongju, Republic of Korea",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2022.loresmt-1.14/",
    pages = "107--117",
    abstract = "Aligned word embeddings have become a popular technique for low-resource natural language processing. Most existing evaluation datasets are generated automatically from machine translations systems, so they have many errors and exist only for high-resource languages. We introduce the Wiktionary bilingual lexicon collection, which provides high-quality human annotated translations for words in 298 languages to English. We use these lexicons to train and evaluate the largest published collection of aligned word embeddings on 157 different languages. All of our code and data is publicly available at \url{https://github.com/mikeizbicki/wiktionary_bli}."
}