NTT-UT Statistical Machine Translation in NTCIR-9 PatentMT

  title={NTT-UT Statistical Machine Translation in NTCIR-9 PatentMT},
  author={Katsuhito Sudoh and Kevin Duh and Hajime Tsukada and Masaaki Nagata and Xianchao Wu and Takuya Matsuzaki and Jun'ichi Tsujii},
This paper describes details of the NTT-UT system in NTCIR9 PatentMT task. One of its key technology is system combination; the final translation hypotheses are chosen from n-bests by different SMT systems in a Minimum Bayes Risk (MBR) manner. Each SMT system includes different technology: syntactic pre-ordering, forest-to-string translation, and using external resources for domain adaptation and target language modeling. 
Highly Cited
This paper has 29 citations. REVIEW CITATIONS
18 Citations
17 References
Similar Papers


Publications citing this paper.
Showing 1-10 of 18 extracted citations


Publications referenced by this paper.

Similar Papers

Loading similar papers…