Journal: | Computación y sistemas |
Database: | |
System number: | 000560454 |
ISSN: | 1405-5546 |
Authors: | Svoboda, Lukáš1 Brychcín, Tomáš1 |
Institutions: | 1University of West Bohemia, Faculty of Applied Sciences, Plzeň. República Checa |
Year: | 2019 |
Season: | Jul-Sep |
Volumen: | 23 |
Number: | 3 |
Pages: | 773-783 |
Country: | México |
Language: | Inglés |
Document type: | Artículo |
English abstract | In this paper we evaluate our new approach based on the Continuous Bag-of-Words and Skip-gram models enriched with global context information on highly inflected Czech language and compare it with English results. As a source of information we use Wikipedia, where articles are organized in a hierarchy of categories. These categories provide useful topical information about each article. Both models are evaluated on standard word similarity and word analogy datasets. Proposed models outperform other word representation methods when similar size of training data is used. Model provide similar performance especially with methods trained on much larger datasets. |
Disciplines: | Ciencias de la computación |
Keyword: | Inteligencia artificial |
Keyword: | Highly inflected language, Word embeddings, Artificial intelligence |
Full text: | Texto completo (Ver HTML) Texto completo (Ver PDF) |