@inproceedings{st-arnaud-etal-2017-identifying,
    title = "Identifying Cognate Sets Across Dictionaries of Related Languages",
    author = "St Arnaud, Adam  and
      Beck, David  and
      Kondrak, Grzegorz",
    editor = "Palmer, Martha  and
      Hwa, Rebecca  and
      Riedel, Sebastian",
    booktitle = "Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing",
    month = sep,
    year = "2017",
    address = "Copenhagen, Denmark",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/D17-1267/",
    doi = "10.18653/v1/D17-1267",
    pages = "2519--2528",
    abstract = "We present a system for identifying cognate sets across dictionaries of related languages. The likelihood of a cognate relationship is calculated on the basis of a rich set of features that capture both phonetic and semantic similarity, as well as the presence of regular sound correspondences. The similarity scores are used to cluster words from different languages that may originate from a common proto-word. When tested on the Algonquian language family, our system detects 63{\%} of cognate sets while maintaining cluster purity of 70{\%}."
}