International Workshop on Spoken Language Translation (IWSLT) 2006

Keihanna Science City, Kyoto, Japan
November 27-28, 2006

Phrase Reordering for Statistical Machine Translation Based on Predicate-Argument Structure

Mamoru Komachi (1), Yuji Matsumoto (1), Masaaki Nagata (2)

(1) Nara Insitute of Science and Technology, Nara, Japan
(2) NTT Communication Science Laboratories, Seika-cho, Soraku-gun, Kyoto, Japan

In this paper, we describe a novel phrase reordering model based on predicate-argument structure. Our phrase reordering method utilizes a general predicate-argument structure analyzer to reorder source language chunks based on predicate-argument structure. We explicitly model long-distance phrase alignments by reordering arguments and predicates. The reordering approach is applied as a preprocessing step in training phase of a phrase-based statistical MT system. We report experimental results in the evaluation campaign of IWSLT 2006.

Full Paper     Presentation

Bibliographic reference.  Komachi, Mamoru / Matsumoto, Yuji / Nagata, Masaaki (2006): "Phrase reordering for statistical machine translation based on predicate-argument structure", In IWSLT-2006, 77-82.