Neural network based dependency parser
Organisatsiooni nimi
Natural Language Processing
Kokkuvõte
Dependency 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.
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 aasta
2016-2017
Juhendaja
Kairit Sirts
Suhtlemiskeel(ed)
eesti keel, inglise keel
Nõuded kandideerijale
Programming 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