Karolína Hořeňovská


2019

pdf bib
An evaluation of Czech word embeddings
Karolína Hořeňovská
Proceedings of the 22nd Nordic Conference on Computational Linguistics

We present an evaluation of Czech low-dimensional distributed word representations, also known as word embeddings. We describe five different approaches to training the models and three different corpora used in training. We evaluate the resulting models on five different datasets, report the results and provide their further analysis.
Search
Co-authors
    Venues