Leveraging “Commonalities” in low-resource setting

Organization
TartuNLP
Abstract
In this thesis, the goal is to transfer the NLP capabilities from high-resourced languages to a low-resourced language settings. In particular, this work leverages the transformer-based pretrained models and investigates the knowledge transfer possibilities on related languages, distant languages, and within the target (low-resourced) language.
The focus is on Estonian (as the target language) and on the Sentiment Analysis task.
Graduation Theses defence year
2023-2024
Supervisor
Somnath Banerjee, Siim Orasmaa
Spoken language (s)
Estonian, English
Requirements for candidates
Level
Bachelor, Masters
Keywords
#NLP, #LanguageModels, #Sentiment Analysis

Application of contact

 
Name
Somanth Banerjee, Siim Orasmaa
Phone
E-mail
somnath.banerjee@ut.ee; siim.orasmaa@ut.ee
See more
http://www.ut.ee//~somnath/