Other formats:
BibTeX
LaTeX
RIS
@inproceedings{1809740,
author = {Herman, Ondřej},
address = {Brno},
booktitle = {Recent Advances in Slavonic Natural Language Processing (RASLAN 2021)},
editor = {Horák, Rychlý, Rambousek},
keywords = {Word embeddings; Sketch Engine; Corpora},
howpublished = {tištěná verze "print"},
language = {eng},
location = {Brno},
isbn = {978-80-263-1670-1},
pages = {41-46},
publisher = {Tribun EU},
title = {Precomputed Word Embeddings for 15+ Languages},
url = {https://raslan2021.nlp-consulting.net/},
year = {2021}
}
TY - JOUR
ID - 1809740
AU - Herman, Ondřej
PY - 2021
TI - Precomputed Word Embeddings for 15+ Languages
PB - Tribun EU
CY - Brno
SN - 9788026316701
KW - Word embeddings
KW - Sketch Engine
KW - Corpora
UR - https://raslan2021.nlp-consulting.net/
N2 - Word embeddings serve as an useful resource for many downstream natural language processing tasks. The embeddings map or embed the lexicon of a language onto a vector space, in which various operations can be carried out easily using the established machinery of linear algebra. The unbounded nature of the language can be problematic and word embeddings provide a way of compressing the words into a manageable dense space. The position of a word in the vector space is given by the context the word appears in, or, as the distributional hypothesis postulates, a word is characterized by the company it keeps [2]. As similar words appear in similar contexts, their positions will also be close to each other in the embedding vector space. Because of this many useful semantical properties of words are preserved in the embedding vector space.
ER -
HERMAN, Ondřej. Precomputed Word Embeddings for 15+ Languages. In Horák, Rychlý, Rambousek. \textit{Recent Advances in Slavonic Natural Language Processing (RASLAN 2021)}. Brno: Tribun EU, 2021, p.~41-46. ISBN~978-80-263-1670-1.
|
