DFKI's system for WMT16 IT-domain task, including analysis of systematic errors

Eleftherios Avramidis, Aljoscha Burchardt, Vivien Macketanz, Ankit Srivastava

In: Proceedings of the First Conference on Machine Translation. Workshop on Statistical Machine Translation (WMT-16) located at The 54th Annual Meeting of the Association for Computational Linguistics August 11-12 Berlin Germany Pages 415-422 Association for Computational Linguistics 8/2016.


We are presenting a hybrid MT approach in the WMT2016 Shared Translation Task for the IT-Domain. Our work consists of several translation components based on rule-based and statistical approaches that feed into an informed selection mechanism. Additions to last year’s submission include a WSD component, a syntactically-enhanced component and several improvements to the rule-based component, relevant to the particular domain. We also present detailed human evaluation on the output of all translation components, focusing on particular systematic errors.


Weitere Links

W16-2329.pdf (pdf, 113 KB )

German Research Center for Artificial Intelligence
Deutsches Forschungszentrum für Künstliche Intelligenz