Word2vec / nlpl_13

Information

A word2vec model trained by Andrey Kutuzov ( [email protected] ) on a vocabulary of size 262269 corresponding to 4815382730 tokens from the dataset Gigaword_5th_Edition . The model is trained with the following properties: lemmatization and postag with the algorith Global Vectors with window of 5 and dimension of 300.

How to use?

from gensim.models import KeyedVectors
from huggingface_hub import hf_hub_download
model = KeyedVectors.load_word2vec_format(hf_hub_download(repo_id="Word2vec/nlpl_13", filename="model.bin"), binary=True, unicode_errors="ignore")

Citation

Fares, Murhaf; Kutuzov, Andrei; Oepen, Stephan & Velldal, Erik (2017). Word vectors, reuse, and replicability: Towards a community repository of large-text resources, In Jörg Tiedemann (ed.), Proceedings of the 21st Nordic Conference on Computational Linguistics, NoDaLiDa, 22-24 May 2017. Linköping University Electronic Press. ISBN 978-91-7685-601-7

This archive is part of the NLPL Word Vectors Repository ( http://vectors.nlpl.eu/repository/ ), version 2.0, published on Friday, December 27, 2019. Please see the file 'meta.json' in this archive and the overall repository metadata file http://vectors.nlpl.eu/repository/20.json for additional information. The life-time identifier for this model is: http://vectors.nlpl.eu/repository/20/13.zip