Predicting Typological Features in WALS using Language Embeddings and Conditional Probabilities: ÚFAL Submission to the SIGTYP 2020 Shared Task

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.

Keywords

• predicting
• typological
• features
• wals
• using
• language
• embeddings
• conditional
• probabilities
• úfal
• submission
• sigtyp
• 2020
• shared
• task