The goal of this thesis is to describe and build a system for neural machine translation. System is built with recurrent neural networks - encoder-decoder architecture in particular. The result is a nmt library used to conduct experiments with different model parameters. Results of the experiments are compared with system built with the statistical tool Moses.
| Identifer | oai:union.ndltd.org:nusl.cz/oai:invenio.nusl.cz:386020 |
| Date | January 2018 |
| Creators | Holcner, Jonáš |
| Contributors | Beneš, Karel, Szőke, Igor |
| Publisher | Vysoké učení technické v Brně. Fakulta informačních technologií |
| Source Sets | Czech ETDs |
| Language | Czech |
| Detected Language | English |
| Type | info:eu-repo/semantics/masterThesis |
| Rights | info:eu-repo/semantics/restrictedAccess |
Page generated in 0.0023 seconds