Tracking Typological Traits of Uralic Languages in Distributed Language Representations

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

Documents

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
Original languageEnglish
Title of host publicationProceedings, Fourth International Workshop on Computational Linguistics for Uralic Languages
PublisherAssociation for Computational Linguistics
Publication date2018
Pages78-88
DOIs
Publication statusPublished - 2018
EventFourth International Workshop on Computational Linguistics for Uralic Languages - Helsinki, Finland
Duration: 8 Jan 20189 Jan 2018

Conference

ConferenceFourth International Workshop on Computational Linguistics for Uralic Languages
LandFinland
ByHelsinki
Periode08/01/201809/01/2018

Number of downloads are based on statistics from Google Scholar and www.ku.dk


No data available

ID: 195046443