arvutiteaduse instituudi lõputööde teemade register


Neural network based dependency parser
Organisatsiooni nimiNatural Language Processing
KokkuvõteDependency parser is one of the core natural language processing tools that expresses the syntactic structure of sentences with directed dependency graphs. Recently, neural network based dependency parsers have reached state of the art performance in English.

The goal of this project is to experimentally train neural network based dependency parsers on Estonian using universal dependencies treebank (https://github.com/UniversalDependencies/UD_Estonian). In principle, the project can be about any other language of interest as well, except for English that already has high-quality parsers available.
Lõputöö kaitsmise aasta2016-2017
JuhendajaKairit Sirts
Suhtlemiskeel(ed)eesti keel, inglise keel
Nõuded kandideerijaleProgramming in python, general understanding of neural networks, interest in working with natural language data
Tase Bakalaureus, Magister
Märksõnad
Kandideerimise kontakt
Nimi Kairit Sirts
Tel
E-mail kairit.sirts@ut.ee


ati.study@lists.ut.ee