Makrai Márton: Comparison of distributed language models on medium-resourced languages.
Preview |
Cikk, tanulmány, mű
msznykonf_011_022-033.pdf Download (191kB) | Preview |
Abstract
word2vec and GloVe are the two most successful open-source tools that compute distributed language models from gigaword corpora. word2vec implements the neural network style architectures skip-gram and cbow, learning parameters using each word as a training sample, while GloVe factorizes the cooccurrence-matrix (or more precisely a matrix of conditional probabilities) as a whole. In the present work, we compare the two systems on two tasks: a Hungarian equivalent of a popular word analogy task and word translation between European languages including medium-resourced ones e.g. Hungarian, Lithuanian and Slovenian.
| Item Type: | Conference or Workshop Item |
|---|---|
| Journal or Publication Title: | Magyar Számítógépes Nyelvészeti Konferencia |
| Date: | 2015 |
| Volume: | 11 |
| ISBN: | 978-963-306-359-0 |
| Page Range: | pp. 22-33 |
| Language: | Hungarian |
| Event Title: | Magyar Számítógépes Nyelvészeti Konferencia (11.) (2015) (Szeged) |
| Related URLs: | http://acta.bibl.u-szeged.hu/58552/ |
| Uncontrolled Keywords: | Nyelvészet - számítógép alkalmazása |
| Additional Information: | Bibliogr.: 33. p. ; összefoglalás angol nyelven |
| Date Deposited: | 2019. Jun. 28. 08:09 |
| Last Modified: | 2026. Feb. 24. 08:10 |
| URI: | http://acta.bibl.u-szeged.hu/id/eprint/58918 |
Actions (login required)
 |
View Item |
