Integrating a Rule-based with a Hierarchical Translation System

Yu Chen, Andreas Eisele

In: Daniel Tapias , Mike Rosner , Stelios Piperidis , Jan Odjik , Joseph Mariani , Bente Maegaard , Khalid Choukri , Nicoletta Calzolari (Conference Chair) (editor). Proceedings of the Seventh conference on International Language Resources and Evaluation. International Conference on Language Resources and Evaluation (LREC-10) May 19-21 La Valletta Malta Pages 1746-1752 ISBN 2-9517408-6-7 European Language Resources Association (ELRA) 5/2010.


Recent developments on hybrid systems that combine rule-based machine translation (RBMT) systems with statistical machine translation (SMT) generally neglect the fact that RBMT systems tend to produce more syntactically well-formed translations than data-driven systems. This paper proposes a method that alleviates this issue by preserving more useful structures produced by RBMT systems and utilizing them in a SMT system that operates on hierarchical structures instead of flat phrases alone. For our experiments, we use Joshua as the decoder (Li et al., 2009). It is the first attempt towards a tighter integration of MT systems from different paradigms that both support hierarchical analyses. Preliminary results show consistent improvements over the previous approach.

754_Paper.pdf (pdf, 363 KB )

German Research Center for Artificial Intelligence
Deutsches Forschungszentrum für Künstliche Intelligenz