Statistical machine translation using large j/e parallel corpus and long phrase tables

@inproceedings{Murakami2007StatisticalMT,
  title={Statistical machine translation using large j/e parallel corpus and long phrase tables},
  author={Jin'ichi Murakami and Masato Tokuhisa and Satoru Ikehara},
  booktitle={IWSLT},
  year={2007}
}
Our statistical machine translation system that uses large Japanese-English parallel sentences and long phrase tables is described. We collected 698,973 Japanese-English parallel sentences, and we used long phrase tables. Also, we utilized general tools for statistical machine translation, such as ”Giza++”[1], ”moses”[2], and ”training-phrasemodel.perl”[3]. We used these data and these tools, We challenge the contest for IWSLT07. In which task was the result (0.4321 BLEU) obtained. 

Tables, Results, and Topics from this paper.

Key Quantitative Results

  • In which task was the result (0.4321 BLEU) obtained.

Explore Further: Topics Discussed in This Paper

References

Publications referenced by this paper.
SHOWING 1-4 OF 4 REFERENCES

//www.statmt.org/moses/ [3] training-release-1.3.tgz

  • Http Moses
  • //www.statmt.org/moses/ [3] training-release-1.3…
1 Excerpt

Genius English-Japanese Dictionary ISBN4-469-04131

  • Genius English-Japanese Dictionary ISBN4-469…

The SRI Language Modeling Toolkit

  • Srilm
  • The SRI Language Modeling Toolkit

http://home.alc.co.jp/db/owa/engt structure?stg=4

  • http://home.alc.co.jp/db/owa/engt structure?stg=4

Similar Papers

Loading similar papers…