Evaluating a Machine Translation System in a Technical Support Scenario

Rosa Del Gaudio, Aljoscha Burchardt, Arle Richard Lommel

In: Jan Hajič, António Branco (Hrsg.). Proceedings of the 1st Deep Machine Translation Workshop. Deep Machine Translation Workshop (DMTW-2015). Deep Machine Translation Workshop (DMTW-2015) September 3-4 Prague Czech Republic Seiten 39-47 ISBN 978-80-904571-7-1 Charles University in Prague, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics 9/2015.


In this document we report on a user scenario based evaluation aiming at assessing the perfor- mance of a machine translation (MT) system in a real context of use. This extrinsic evaluation exemplifies a framework that makes it possible to estimate MT performance and to verify if im- provements of MT technology lead to better performance in a real usage scenario. We report on the evaluation of Moses baselines for several languages in a cross-lingual IT helpdesk scenario.


Weitere Links

evaluating-machine-translation.pdf (pdf, 462 KB )

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence