NTT-NAIST SMT Systems for IWSLT 2013

@inproceedings{Sudoh2013NTTNAISTSS,
  title={NTT-NAIST SMT Systems for IWSLT 2013},
  author={Katsuhito Sudoh and Graham Neubig and Kevin Duh and Hajime Tsukada},
  year={2013}
}
This paper presents NTT-NAIST SMT systems for EnglishGerman and German-English MT tasks of the IWSLT 2013 evaluation campaign. The systems are based on generalized minimum Bayes risk system combination of three SMT systems: forest-to-string, hierarchical phrase-based, phrasebased with pre-ordering. Individual SMT systems include data selection for domain adaptation, rescoring using recurrent neural net language models, interpolated language models, and compound word splitting (only for German… CONTINUE READING
2 Citations
25 References
Similar Papers

Similar Papers

Loading similar papers…