A comparison of statistical and neural machine translation for Slovene, Serbian and Croatian

View/ Open
Date
2018-09-20Author
Arcan, Mihael
Metadata
Show full item recordUsage
This item's downloads: 195 (view details)
Recommended Citation
Arcan, Mihael. (2018). A comparison of Statistical and Neural Machine Translation for Slovene, Serbian and Croatian. Paper presented at the Language Technologies and Digital Humanities 2018, University of Ljubljana, Ljubljana, Slovenia, 20-21 September.
Abstract
In this paper we present a comparison of translation quality using of Statistical Machine Translation (SMT) and Neural Machine Translation (NMT), considering translation directions between English, Slovene, Serbian and Croatian. Our experiments show that on a reduced
training dataset with around two million sentences, SMT outperforms the NMT neural models. Furthermore, we present experiments
with enlarged neural architectures, using 1,000 nodes and 4 hidden layers, which shows improved translation quality in terms of the
BLEU metric