Further Experiments with Shallow Hybrid MT Systems

Christian Federmann, Andreas Eisele, Hans Uszkoreit, Yu Chen, Sabine Hunsicker, Jia Xu

In: Chris Callison-Burch , Philipp Koehn , Christof Monz , Kay Peterson , Omar Zaidan (Hrsg.). Proceedings of the Joint Fifth Workshop on Statistical Machine Translation and MetricsMATR. Workshop on Statistical Machine Translation (WMT-10) befindet sich ACL 2010 July 15-16 Uppsala Sweden Seiten 77-81 ACL 7/2010.


We describe our hybrid machine translation system which has been developed for and used in the WMT10 shared task. We compute translations from a rule-based MT system and combine the resulting translation "templates" with partial phrases from a state-of-the-art phrase-based, statistical MT engine. Phrase substitution is guided by several decision factors, a continuation of previous work within our group. For the shared task, we have computed translations for six language pairs including English, German, French and Spanish. Our experiments have shown that our shallow substitution approach can effectively improve the translation result from the RBMT system; however it has also become clear that a deeper integration is needed to further improve translation quality.


Weitere Links

FedermannEA-WMT2010.pdf (pdf, 346 KB )

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence