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.

• Type: Conference
• Year: 2009
• Where: CICLING
• Authors: John Tinsley, Mary Hearne, Andy Way
• Keywords: CICLING 2009, Natural Language Processing, Parallel Corpora, Parallel Treebanks