RTM results for Predicting Translation Performance

Ergun Biçici


Abstract
With improved prediction combination using weights based on their training performance and stacking and multilayer perceptrons to build deeper prediction models, RTMs become the 3rd system in general at the sentence-level prediction of translation scores and achieve the lowest RMSE in English to German NMT QET results. For the document-level task, we compare document-level RTM models with sentence-level RTM models obtained with the concatenation of document sentences and obtain similar results.
Anthology ID:
W18-6458
Volume:
Proceedings of the Third Conference on Machine Translation: Shared Task Papers
Month:
October
Year:
2018
Address:
Belgium, Brussels
Editors:
Ondřej Bojar, Rajen Chatterjee, Christian Federmann, Mark Fishel, Yvette Graham, Barry Haddow, Matthias Huck, Antonio Jimeno Yepes, Philipp Koehn, Christof Monz, Matteo Negri, Aurélie Névéol, Mariana Neves, Matt Post, Lucia Specia, Marco Turchi, Karin Verspoor
Venue:
WMT
SIG:
SIGMT
Publisher:
Association for Computational Linguistics
Note:
Pages:
765–769
Language:
URL:
https://aclanthology.org/W18-6458/
DOI:
10.18653/v1/W18-6458
Bibkey:
Cite (ACL):
Ergun Biçici. 2018. RTM results for Predicting Translation Performance. In Proceedings of the Third Conference on Machine Translation: Shared Task Papers, pages 765–769, Belgium, Brussels. Association for Computational Linguistics.
Cite (Informal):
RTM results for Predicting Translation Performance (Biçici, WMT 2018)
Copy Citation:
PDF:
https://aclanthology.org/W18-6458.pdf