Published August 6, 2020
| Version 1.0.0
Dataset
Open
Word2Vec model - Czech wikipedia
Creators
- 1. Faculty of Information Technology, Czech Technical University in Prague + Faculty of Mathematics and Physics, Charles University
- 2. Faculty of Mathematics and Physics, Charles University
Description
Word2Vec embedding model trained on Czech wikipedia (from April 2020) corpus using gensim implementation with the following parameters in addition to default settings:
- vector dimension = \(400\),
- window size = \(10\),
- word minimum count = \(10\),
- sample = \(10^{-5}\).
Notes
This work was supported by the Czech Science Foundation (GAČR),grant number 19-01641S.