The WMT’18 Morpheval test suites for English-Czech, English-German, English-Finnish and Turkish-English




Franck Burlot, Yves Scherrer, Vinit Ravishankar, Ondřej Bojar, Stig-Arne Grönroos, Maarit Koponen, Tommi Nieminen, François Yvon

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

Conference on Machine Translation

Stroudsburg, PA, USA

2018

Proceedings of the Third Conference on Machine Translation (WMT) : Shared Task Papers

550

564

978-1-948087-81-0

http://www.statmt.org/wmt18/pdf/WMT060.pdf

https://research.utu.fi/converis/portal/detail/Publication/36171463



Progress in the quality of machine translation output calls for new automatic evaluation procedures and metrics. In this paper, we extend the Morpheval protocol introduced by Burlot and Yvon (2017) for the English-to-Czech and English-to-Latvian translation directions to three additional language pairs, and report its use to analyze the results of WMT2018’s participants for these language pairs. Considering additional, typologically varied source and target languages also enables us to draw some generalizations regarding this morphology-oriented evaluation procedure.

Last updated on 2024-26-11 at 14:13