A Survey of Cross-lingual Word Embedding Models
Identifikátory výsledku
Kód výsledku v IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F19%3A10427057" target="_blank" >RIV/00216208:11320/19:10427057 - isvavai.cz</a>
Výsledek na webu
<a href="https://www.jair.org/index.php/jair/article/view/11640" target="_blank" >https://www.jair.org/index.php/jair/article/view/11640</a>
DOI - Digital Object Identifier
—
Alternativní jazyky
Jazyk výsledku
angličtina
Název v původním jazyce
A Survey of Cross-lingual Word Embedding Models
Popis výsledku v původním jazyce
Cross-lingual representations of words enable us to reason about word meaning inmultilingual contexts and are a key facilitator of cross-lingual transfer when developingnatural language processing models for low-resource languages. In this survey, we provide acomprehensive typology of cross-lingual word embedding models. We compare their datarequirements and objective functions. The recurring theme of the survey is that many ofthe models presented in the literature optimize for the same objectives, and that seeminglydifferent models are often equivalent, modulo optimization strategies, hyper-parameters,and such. We also discuss the different ways cross-lingual word embeddings are evaluated,as well as future challenges and research horizons.
Název v anglickém jazyce
A Survey of Cross-lingual Word Embedding Models
Popis výsledku anglicky
Cross-lingual representations of words enable us to reason about word meaning inmultilingual contexts and are a key facilitator of cross-lingual transfer when developingnatural language processing models for low-resource languages. In this survey, we provide acomprehensive typology of cross-lingual word embedding models. We compare their datarequirements and objective functions. The recurring theme of the survey is that many ofthe models presented in the literature optimize for the same objectives, and that seeminglydifferent models are often equivalent, modulo optimization strategies, hyper-parameters,and such. We also discuss the different ways cross-lingual word embeddings are evaluated,as well as future challenges and research horizons.
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
2019
Kód důvěrnosti údajů
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů