Neural machine translation for Hungarian

In the scope of this research, we aim to give an overview of the currently existing solutions for machine translation and we assess their performance on the English-Hungarian language pair. Hungarian is considered to be a challenging language for machine translation because it has a highly different...

Full description

Saved in:
Bibliographic Details
Published inActa linguistica academica Vol. 69; no. 4; pp. 501 - 520
Main Authors Laki, László János, Yang, Zijian Győző
Format Journal Article
LanguageEnglish
Published Budapest Akadémiai Kiadó 12.12.2022
Academic Publishing House
Akademiai Kiado Zrt
Subjects
English language
Hungarian language
Machine translation
Translation Studies
Marian NMT
M2M100
mBART
neural machine translation
BART
mT5
Online AccessGet full text

Cover

More Information
Summary:In the scope of this research, we aim to give an overview of the currently existing solutions for machine translation and we assess their performance on the English-Hungarian language pair. Hungarian is considered to be a challenging language for machine translation because it has a highly different grammatical structure and word ordering compared to English. We probed various machine translation systems from both academic and industrial applications. One key highlight of our work is that our models (Marian NMT, BART) performed significantly better than the solutions offered by most of the market-leader multinational companies. Finally, we fine-tuned different pre-finetuned models (mT5, mBART, M2M100) for English-Hungarian translation, which achieved state-of-the-art results in our test corpora.
ISSN:2559-8201
2560-1016
DOI:10.1556/2062.2022.00576