Summary of the paper
| Title | Integrating a Rule-based with a Hierarchical Translation System |
|---|---|
| Authors | Yu Chen and Andreas Eisele |
| Abstract | Recent developments on hybrid systems that combine rule-based machinetranslation (RBMT) systems with statistical machine translation (SMT) generallyneglect the fact that RBMT systems tend to produce more syntacticallywell-formed translations than data-driven systems. This paper proposes a methodthat alleviates this issue by preserving more useful structures produced byRBMT systems and utilizing them in a SMT system that operates on hierarchicalstructures instead of flat phrases alone. For our experiments, we use Joshua asthe decoder. It is the first attempt towards a tighter integration of MTsystems from different paradigms that both support hierarchical analysis.Preliminary results show consistent improvements over the previous approach. |
| Language | Tools, systems, applications |
| Topics | Machine Translation, SpeechToSpeech Translation, Multilinguality, Tools, systems, applications |
Full paper  |
Integrating a Rule-based with a Hierarchical Translation System |
| Bibtex | @InProceedings{CHEN10.754, author = {Yu Chen and Andreas Eisele}, title = {Integrating a Rule-based with a Hierarchical Translation System}, booktitle = {Proceedings of the Seventh conference on International Language Resources and Evaluation (LREC'10)}, year = {2010}, month = {may}, date = {19-21}, address = {Valletta, Malta}, editor = {Nicoletta Calzolari (Conference Chair), Khalid Choukri, Bente Maegaard, Joseph Mariani, Jan Odjik, Stelios Piperidis, Mike Rosner, Daniel Tapias}, publisher = {European Language Resources Association (ELRA)}, isbn = {2-9517408-6-7}, language = {english} } |