tailieunhanh - Báo cáo khoa học: "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. . | Topological Ordering of Function Words in Hierarchical Phrase-based Translation Hendra Setiawan1 and Min-Yen Kan2 and Haizhou Li3 and Philip Resnik1 1 University of Maryland Institute for Advanced Computer Studies 2School of Computing National University of Singapore 3Human Language Technology Institute for Infocomm Research Singapore hendra resnik @ kanmy@ hli@ Abstract 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 difficult to distinguish many implausible reorderings from those that are linguistically plausible. Rather than appealing to annotation-driven syntactic modeling we address this problem by observing the influential 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 significant gains in performance. 1 Introduction Hierarchical phrase-based models Chiang 2005 Chiang 2007 offer a number of attractive benefits in statistical machine translation SMT while maintaining the strengths of phrase-based systems Koehn et al. 2003 . The most important of these is the ability to model long-distance reordering efficiently. To model such a reordering a hierarchical phrase-based system demands no additional parameters since long and short distance reorderings are modeled identically using synchronous context free grammar SCFG rules. The same rule depending on its topological ordering - . its position in the hierarchical structure - can affect both short and long spans of text. Interestingly hierarchical phrase-based models provide this benefit without making any linguistic commitments beyond the structure of the model. However the system s lack of .