Syntactic phrase-based statistical machine translation
Hassan, Hany and Hearne, Mary and Way, Andy and Sima'an, Khalil (2006) Syntactic phrase-based statistical machine translation. In: IEEE Spoken Language Technology Workshop, 2006, 10-13 December 2006, Palm Beach, Aruba. ISBN 1-4244-0872-5
Full text available as:
Phrase-based statistical machine translation (PBSMT) systems represent the dominant approach in MT today. However, unlike systems in other paradigms, it has proven difficult to date to incorporate syntactic knowledge in order to improve translation quality. This paper improves on recent research which uses 'syntactified' target language phrases, by incorporating supertags as constraints to better resolve parse tree fragments. In addition, we do not impose any sentence-length limit, and using a log-linear decoder, we outperform a state-of-the-art PBSMT system by over 1.3 BLEU points (or 3.51% relative) on the NIST 2003 Arabic-English test corpus.
Archive Staff Only: edit this record