What level of quality can neural machine translation attain on literary text?
Toral, AntonioORCID: 0000-0003-2357-2960 and Way, AndyORCID: 0000-0001-5736-5930
(2018)
What level of quality can neural machine translation attain on literary text?
In: Moorkens, JossORCID: 0000-0003-4864-5986, Castilho, SheilaORCID: 0000-0002-8416-6555, Gaspari, FedericoORCID: 0000-0003-3808-8418 and Doherty, S, (eds.)
Translation Quality Assessment: From Principles to Practice.
Machine Translation: Technologies and Applications book series (MATRA), 1
.
Springer, Berlin/Heidelberg, 263 -287.
ISBN 978-3-319-91240-0
Given the rise of the new neural approach to machine translation (NMT) and its promising performance on different text types, we assess the translation quality it can attain on what is perceived to be the greatest challenge for MT: literary text. Specifically, we target novels, arguably the most popular type of literary text. We build a literary-adapted NMT system for the English-to-Catalan translation direction and evaluate it against a system pertaining to the previous dominant paradigm in MT: statistical phrase-based MT (PBSMT). To this end, for the first time we train MT systems, both NMT and PBSMT, on large amounts of literary text (over 100 million words) and evaluate them on a set of 12 widely known novels spanning from the 1920s to the present day. According to the BLEU automatic evaluation metric, NMT is significantly better than PBSMT (p
This item is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 3.0 License. View License
Funders:
European Association for Machine Translation through its 2015 sponsorship of activities programme (project PiPeNovel)., ADAPT Centre for Digital Content Technology, funded under the (SFI) Research Centres Programme (Grant 13/RC/2106)
ID Code:
24599
Deposited On:
06 Jul 2020 10:18 by
Vidatum Academic
. Last Modified 12 Aug 2020 10:52