University of Cambridge > Talks.cam > Language Technology Lab Seminars > Language Adaptation experiments: Cross-lingual embeddings for related languages

Language Adaptation experiments: Cross-lingual embeddings for related languages

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Dimitri Kartsaklis.

We do not have sufficient annotated resources for many languages. For example, out of the 47 languages in the Universal Depencies set only two languages have treebanks exceeding 1 mln words, while many languages are not represented at all. However, we can use typological links between the languages to produce better computational models for lesser-resourced languages (recipients) by transferring information from better resourced ones (donors). In this talk I report my experience of building and using cross-lingual embeddings with added constraints such as the Weighted Levenshtein Distance.

This talk is part of the Language Technology Lab Seminars series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2024 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity