Although linguistic typology has a long history, computational approaches have only recently gained popularity. The use of distributed representations in computational linguistics has also become increasingly popular. A recent development is to learn distributed representations of language, such that typologically similar languages are spatially close to one another. Although empirical successes have been shown for such language representations, they have not been subjected to much typological probing. In this paper, we first look at whether this type of language representations are empirically useful for model transfer between Uralic languages in deep neural networks. We then investigate which typological features are encoded in these representations by attempting to predict features in the World Atlas of Language Structures, at various stages of fine-tuning of the representations. We focus on Uralic languages, and find that some typological traits can be automatically inferred with accuracies well above a strong baseline.
View on arXiv