DFKI-LT - Integrating a Rule-based with a Hierarchical Translation System

Yu Chen, Andreas Eisele
Integrating a Rule-based with a Hierarchical Translation System
in: Daniel Tapias, Mike Rosner, Stelios Piperidis, Jan Odjik, Joseph Mariani, Bente Maegaard, Khalid Choukri, Nicoletta Calzolari (Conference Chair) (eds.):
2 Proceedings of the Seventh conference on International Language Resources and Evaluation, Pages 1746-1752, La Valletta, Malta, European Language Resources Association (ELRA), 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.
Files: BibTeX, 754_Paper.pdf