Tree-to-String Alignment Template for Statistical Machine Translation

We present a novel translation model based on tree-to-string alignment template (TAT) which describes the alignment between a source parse tree and a target string. A TAT is capable of generating both terminals and non-terminals and performing reordering at both low and high levels. The model is linguistically syntaxbased because TATs are extracted automatically from word-aligned, source side parsed parallel texts. To translate a source sentence, we first employ a parser to produce a source parse tree and then apply TATs to transform the tree into a target string. Our experiments show that the TAT-based model significantly outperforms Pharaoh, a state-of-the-art decoder for phrase-based models.

• Type: Conference
• Year: 2006
• Where: ACL
• Authors: Yang Liu, Qun Liu, Shouxun Lin
• Keywords: ACL 2006, ACL 2007, Source Parse Tree, Target String, Tree-to-string Alignment Template