Browse DORAS
Browse Theses
Search
Latest Additions
Creative Commons License
Except where otherwise noted, content on this site is licensed for use under a:

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:

[img]
Preview
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
131Kb

Abstract

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.

Item Type:Conference or Workshop Item (Paper)
Event Type:Workshop
Refereed:Yes
Uncontrolled Keywords:log-linear decoder , parse tree fragments , syntactic knowledge; syntactic phrase-based statistical machine translation; translation quality;
Subjects:Computer Science > Machine translating
DCU Faculties and Centres:Research Initiatives and Centres > National Centre for Language Technology (NCLT)
DCU Faculties and Schools > Faculty of Engineering and Computing > School of Computing
Published in:2006 IEEE Spoken Language Technology Workshop. . Institute of Electrical and Electronics Engineers. ISBN 1-4244-0872-5
Publisher:Institute of Electrical and Electronics Engineers
Official URL:http://dx.doi.org/10.1109/SLT.2006.326799
Copyright Information:©2006 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
Funders:Science Foundation Ireland, SFI 05/IN/1732
ID Code:15280
Deposited On:11 Mar 2010 11:32 by DORAS Administrator. Last Modified 27 Apr 2010 17:06

Download statistics

Archive Staff Only: edit this record