@inproceedings{rama-2018-similarity,
    title = "Similarity Dependent {C}hinese Restaurant Process for Cognate Identification in Multilingual Wordlists",
    author = "Rama, Taraka",
    editor = "Korhonen, Anna  and
      Titov, Ivan",
    booktitle = "Proceedings of the 22nd Conference on Computational Natural Language Learning",
    month = oct,
    year = "2018",
    address = "Brussels, Belgium",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/K18-1027/",
    doi = "10.18653/v1/K18-1027",
    pages = "271--281",
    abstract = "We present and evaluate two similarity dependent Chinese Restaurant Process (sd-CRP) algorithms at the task of automated cognate detection. The sd-CRP clustering algorithms do not require any predefined threshold for detecting cognate sets in a multilingual word list. We evaluate the performance of the algorithms on six language families (more than 750 languages) and find that both the sd-CRP variants performs as well as InfoMap and better than UPGMA at the task of inferring cognate clusters. The algorithms presented in this paper are family agnostic and can be applied to any linguistically under-studied language family."
}