Forest-Based Translation

Among syntax-based translation models, the tree-based approach, which takes as input a parse tree of the source sentence, is a promising direction being faster and simpler than its string-based counterpart. However, current tree-based systems suffer from a major drawback: they only use the 1-best parse to direct the translation, which potentially introduces translation mistakes due to parsing errors. We propose a forest-based approach that translates a packed forest of exponentially many parses, which encodes many more alternatives than standard n-best lists. Large-scale exper

• Type: Conference
• Year: 2008
• Where: ACL
• Authors: Haitao Mi, Liang Huang, Qun Liu
• Keywords: ACL 2008, Computational Linguistics, Current Tree-based Systems, Parse Tree, Syntax-based Translation Models