Deeper Machine Translation and Evaluation for German

Eleftherios Avramidis; Vivien Macketanz; Aljoscha Burchardt; Jindrich Helcl; Hans Uszkoreit

In: Jan Hajic; Gertjan van Noord; António Branco (Hrsg.). Proceedings of the 2nd Deep Machine Translation Workshop. Deep Machine Translation Workshop (DMTW), October 21, Lisbon, Portugal, Pages 29-38, ISBN 978-80-88132-02-8, Charles University, Prague, 10/2016.


This paper describes a hybrid Machine Translation (MT) system built for translating from English to German in the domain of technical documentation. The system is based on three different MT engines (phrase-based SMT, RBMT, neural) that are joined by a selection mechanism that uses deep linguistic features within a machine learning process. It also presents a detailed source-driven manual error analysis we have performed using a dedicated “test suite” that contains selected examples of relevant phenomena. While automatic scores show huge differences between the engines, the overall average number or errors they (do not) make is very similar for all systems. However, the detailed error breakdown shows that the systems behave very differently concerning the various phenomena.


Weitere Links

W16-6404.pdf (pdf, 173 KB )

German Research Center for Artificial Intelligence
Deutsches Forschungszentrum für Künstliche Intelligenz