Paper: Syntactic Reordering Integrated with Phrase-Based SMT

ACL ID C08-1027
Title Syntactic Reordering Integrated with Phrase-Based SMT
Venue International Conference on Computational Linguistics
Session Main Conference
Year 2008
  • Jakob Elming (Copenhagen Business School, Copenhagen Denmark)

We present a novel approach to word reordering which successfully integrates syntactic structural knowledge with phrase-based SMT. This is done by con- structing a lattice of alternatives based on automatically learned probabilistic syntactic rules. In decoding, the alter- natives are scored based on the output word order, not the order of the input. Unlike previous approaches, this makes it possible to successfully integrate syntactic reordering with phrase-based SMT. On an English-Danish task, we achieve an absolute improvement in translation qual- ity of 1.1 % BLEU. Manual evaluation supports the claim that the present ap- proach is significantly superior to previous approaches.