Topological Ordering of Function Words in Hierarchical Phrase-based Translation

Hierarchical phrase-based models are attractive because they provide a consistent framework within which to characterize both local and long-distance reorderings, but they also make it dif cult to distinguish many implausible reorderings from those that are linguistically plausible. Rather than appealing to annotationdriven syntactic modeling, we address this problem by observing the in uential role of function words in determining syntactic structure, and introducing soft constraints on function word relationships as part of a standard log-linear hierarchical phrase-based model. Experimentation on Chinese-English and Arabic-English translation demonstrates that the approach yields signi cant gains in performance.

• Type: Journal
• Year: 2009
• Where: ACL
• Authors: Hendra Setiawan, Min-Yen Kan, Haizhou Li, Philip Resnik
• Keywords: ACL 2009, Computational Linguistics, Function Word, Function Word Relationships, Hierarchical Phrase-based Model