Unsupervised Deep Representation Learning for Low-Resourced Languages and Applications
Identifikátory výsledku
Kód výsledku v IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F23%3ACDBZTJC8" target="_blank" >RIV/00216208:11320/23:CDBZTJC8 - isvavai.cz</a>
Výsledek na webu
<a href="https://aran.library.nuigalway.ie/bitstream/handle/10379/17767/PhD_Writing_camera_ready.pdf?sequence=1" target="_blank" >https://aran.library.nuigalway.ie/bitstream/handle/10379/17767/PhD_Writing_camera_ready.pdf?sequence=1</a>
DOI - Digital Object Identifier
—
Alternativní jazyky
Jazyk výsledku
angličtina
Název v původním jazyce
Unsupervised Deep Representation Learning for Low-Resourced Languages and Applications
Popis výsledku v původním jazyce
"In this thesis, we introduce novel state-of-the-art deep models which capture global and contextualnsemantic representations of sentences in a document. We focus on building unsupervised deep models tonefficiently exploit the existing unlabelled datasets for feature extraction. Our contribution also includesndesigning state-of-the-art unsupervised sentence embedding models capable of performing a wide range ofncross-lingual tasks for low-resource scenarios. We raise several research questions at the start of the thesisnand we provide answers supported by state-of-the-art experimental results"
Název v anglickém jazyce
Unsupervised Deep Representation Learning for Low-Resourced Languages and Applications
Popis výsledku anglicky
"In this thesis, we introduce novel state-of-the-art deep models which capture global and contextualnsemantic representations of sentences in a document. We focus on building unsupervised deep models tonefficiently exploit the existing unlabelled datasets for feature extraction. Our contribution also includesndesigning state-of-the-art unsupervised sentence embedding models capable of performing a wide range ofncross-lingual tasks for low-resource scenarios. We raise several research questions at the start of the thesisnand we provide answers supported by state-of-the-art experimental results"
Klasifikace
Druh
O - Ostatní výsledky
CEP obor
—
OECD FORD obor
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Návaznosti výsledku
Projekt
—
Návaznosti
—
Ostatní
Rok uplatnění
2023
Kód důvěrnosti údajů
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů