@inproceedings{jager-2020-imputing,
    title = "Imputing typological values via phylogenetic inference",
    author = {J{\"a}ger, Gerhard},
    editor = "Vylomova, Ekaterina  and
      Ponti, Edoardo M.  and
      Grossman, Eitan  and
      McCarthy, Arya D.  and
      Berzak, Yevgeni  and
      Dubossarsky, Haim  and
      Vuli{\'c}, Ivan  and
      Reichart, Roi  and
      Korhonen, Anna  and
      Cotterell, Ryan",
    booktitle = "Proceedings of the Second Workshop on Computational Research in Linguistic Typology",
    month = nov,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2020.sigtyp-1.5/",
    doi = "10.18653/v1/2020.sigtyp-1.5",
    pages = "36--42",
    abstract = "This paper describes a workflow to impute missing values in a typological database, a sub- set of the World Atlas of Language Structures (WALS). Using a world-wide phylogeny de- rived from lexical data, the model assumes a phylogenetic continuous time Markov chain governing the evolution of typological val- ues. Data imputation is performed via a Max- imum Likelihood estimation on the basis of this model. As back-off model for languages whose phylogenetic position is unknown, a k- nearest neighbor classification based on geo- graphic distance is performed."
}