@inproceedings{vastl-etal-2020-predicting,
    title = "Predicting Typological Features in {WALS} using Language Embeddings and Conditional Probabilities: {{\'U}FAL} Submission to the {SIGTYP} 2020 Shared Task",
    author = "Vastl, Martin  and
      Zeman, Daniel  and
      Rosa, Rudolf",
    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-1.4/",
    doi = "10.18653/v1/2020.sigtyp-1.4",
    pages = "29--35",
    abstract = "We present our submission to the SIGTYP 2020 Shared Task on the prediction of typological features. We submit a constrained system, predicting typological features only based on the WALS database. We investigate two approaches. The simpler of the two is a system based on estimating correlation of feature values within languages by computing conditional probabilities and mutual information. The second approach is to train a neural predictor operating on precomputed language embeddings based on WALS features. Our submitted system combines the two approaches based on their self-estimated confidence scores. We reach the accuracy of 70.7{\%} on the test data and rank first in the shared task."
}