@inbook{2e1562c8c59143dd8a0dacf4254fd6fe,
title = "Training an NMT system for legal texts of a low-resource language variety (South Tyrolean German - Italian)",
abstract = "This paper illustrates the process of training and evaluating NMT systems for a language pair that includes a low-resource language variety. A parallel corpus of legal texts for Italian and South Tyrolean German has been compiled, with South Tyrolean German being the low-resourced language variety. As the size of the compiled corpus is insufficient for the training, we have combined the corpus with several parallel corpora using data weighting at sentence level. We then performed an evaluation of each combination and of two popular commercial systems.",
author = "Antoni Oliver and Sergi {\'A}lvarez and Stemle, {Egon W.} and Elena Chiocchetti",
note = "Publisher Copyright: {\textcopyright} 2024 The authors, {\textcopyright} 2024 European Association for Machine Translation.",
year = "2024",
language = "English",
series = "Proceedings of the 25th Annual Conference of the European Association for Machine Translation, EAMT 2024",
publisher = "European Association for Machine Translation",
pages = "573--579",
editor = "Carolina Scarton and Charlotte Prescott and Chris Bayliss and Chris Oakley and Joanna Wright and Stuart Wrigley and Xingyi Song and Edward Gow-Smith and Rachel Bawden and Sanchez-Cartagena, {V�ctor M.} and Patrick Cadwell and Ekaterina Lapshinova-Koltunski and Vera Cabarrao and Konstantinos Chatzitheodorou and Mary Nurminen and Diptesh Kanojia and Helena Moniz",
booktitle = "Research and Implementations and Case Studies",
}