Paper: A Ranking-based Approach to Word Reordering for Statistical Machine Translation

ACL ID P12-1096
Title A Ranking-based Approach to Word Reordering for Statistical Machine Translation
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2012
Authors

Long distance word reordering is a major challenge in statistical machine translation re- search. Previous work has shown using source syntactic trees is an effective way to tackle this problem between two languages with sub- stantial word order difference. In this work, we further extend this line of exploration and propose a novel but simple approach, which utilizes a ranking model based on word or- der precedence in the target language to repo- sition nodes in the syntactic parse tree of a source sentence. The ranking model is auto- matically derived from word aligned parallel data with a syntactic parser for source lan- guage based on both lexical and syntactical features. We evaluated our approach on large- scale Japanese-English and English-Japanese machine translation tasks, and sho...