Modular Septilingual Neural Machine Translation

Simple item page
dc.contributor.advisorTättar, Andre, juhendaja
dc.contributor.advisorKorotkova, Elizaveta, juhendaja
dc.contributor.authorPurason, Taido
dc.contributor.otherTartu Ülikool. Loodus- ja täppisteaduste valdkondet
dc.contributor.otherTartu Ülikool. Arvutiteaduse instituutet
dc.date.accessioned2023-09-13T11:12:33Z
dc.date.available2023-09-13T11:12:33Z
dc.date.issued2021
dc.description.abstractCurrently, the majority of state-of-the-art multilingual neural machine translation systems use a single universal model which fully shares parameters between all language pairs. The University of Tartu Neural Machine Translation system uses the universal architecture as well, and thus also suffers from the problems associated with it, such as limited capacity per language pair. Previous research has shown that a modularized approach with language-specific encoders and decoders successfully addresses many of the universal model’s shortcomings. This thesis applies the modularized architecture and improves the University of Tartu translation system. Orders of magnitude larger dataset containing 7 languages is used to train the models compared to previous work. The modularized model achieves significantly higher BLEU scores than the University of Tartu model and the baseline universal model on all language pairs.et
dc.identifier.urihttps://hdl.handle.net/10062/92143
dc.language.isoenget
dc.publisherTartu Ülikoolet
dc.rightsopenAccesset
dc.rightsAttribution-NonCommercial-NoDerivatives 4.0 International*
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/*
dc.subjectmachine translationet
dc.subjectmultilingual machine translationet
dc.subjectneural machine translationet
dc.subjectneural networkset
dc.subjectnatural language processinget
dc.subject.otherbakalaureusetöödet
dc.subject.otherinformaatikaet
dc.subject.otherinfotehnoloogiaet
dc.subject.otherinformaticset
dc.subject.otherinfotechnologyet
dc.titleModular Septilingual Neural Machine Translationet
dc.typeThesiset

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
purason_informaatika_2021.pdf
Size:
713.57 KB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

MTAT bakalaureusetööd – Bachelor's theses