Predicting Typological Features in WALS using Language Embeddings and Conditional Probabilities: ÚFAL Submission to the SIGTYP 2020 Shared Task
This work addresses the problem of automating typological feature prediction for linguists, but it is incremental as it builds on existing methods and data.
The paper tackled predicting typological features using the WALS database, achieving a top-ranked accuracy of 70.7% on test data by combining conditional probabilities and neural predictors based on language embeddings.
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.