Exact decoding of phrase-based translation models through Lagrangian relaxation

Author(s)
Chang, Yin-Wen, S.M. Massachusetts Institute of Technology
Thumbnail
DownloadFull printable version (3.587Mb)
Other Contributors
Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science.
Advisor
Michael Collins.
Terms of use
M.I.T. theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. See provided URL for inquiries about permission. http://dspace.mit.edu/handle/1721.1/7582
Metadata
Show full item record
Abstract
This thesis describes two algorithms for exact decoding of phrase-based translation models, based on Lagrangian relaxation. Both methods recovers exact solutions, with certificates of optimality, on over 99% of test examples. The first method is much more efficient than approaches based on linear programming (LP) or integer linear programming (ILP) solvers: these methods are not feasible for anything other than short sentences. We compare our methods to MOSES [6], and give precise estimates of the number and magnitude of search errors that MOSES makes.
Description
Thesis (S.M.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2012.
 
Cataloged from PDF version of thesis.
 
Includes bibliographical references (p. 69-72).
 
Date issued
2012
URI
http://hdl.handle.net/1721.1/70791
Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Publisher
Massachusetts Institute of Technology
Keywords
Electrical Engineering and Computer Science.
Collections