Sciweavers

Share
CICLING
2009
Springer

Exploiting Parallel Treebanks to Improve Phrase-Based Statistical Machine Translation

9 years 10 months ago
Exploiting Parallel Treebanks to Improve Phrase-Based Statistical Machine Translation
We use existing tools to automatically build two parallel treebanks from existing parallel corpora. We then show that combining the data extracted from both the treebanks and the corpora into a single translation model can improve the translation quality in a baseline phrasebased statistical machine translation system.
John Tinsley, Mary Hearne, Andy Way
Added 24 Nov 2009
Updated 24 Nov 2009
Type Conference
Year 2009
Where CICLING
Authors John Tinsley, Mary Hearne, Andy Way
Comments (0)
books