English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Although linguistic typology has a long history, computational approacheshave only recently gained popularity. The use of distributed representations incomputational linguistics has also become increasingly popular. A recentdevelopment is to learn distributed representations of language, such thattypologically similar languages are spatially close to one another. Althoughempirical successes have been shown for such language representations, theyhave not been subjected to much typological probing. In this paper, we firstlook at whether this type of language representations are empirically usefulfor model transfer between Uralic languages in deep neural networks. We theninvestigate which typological features are encoded in these representations byattempting to predict features in the World Atlas of Language Structures, atvarious stages of fine-tuning of the representations. We focus on Uraliclanguages, and find that some typological traits can be automatically inferredwith accuracies well above a strong baseline.

Tracking Typological Traits of Uralic Languages in Distributed Language Representations