Advanced Search

Gaussian alignments in statistical translation models

Research and Teaching Output of the MIT Community

Show simple item record

dc.contributor.advisor Michael J. Collins. en_US Mohammad, Ali (Ali H.) en_US
dc.contributor.other Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science. en_US 2007-01-10T16:48:01Z 2007-01-10T16:48:01Z 2006 en_US 2006 en_US
dc.description Thesis (S.M.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2006. en_US
dc.description Includes bibliographical references (leaves 52-53). en_US
dc.description.abstract Machine translation software has been under development almost since the birth of the electronic computer. Current state-of-the-art methods use statistical techniques to learn how to translate from one natural language to another from a corpus of hand-translated text. The success of these techniques comes from two factors: a simple statistical model and vast training data sets. The standard agenda for improving such models is to enable it to model greater complexity; however, it is a byword within the machine learning community that added complexity must be supported with more training data. Given that current models already require huge amounts of data, our agenda is instead to simplify current models before adding extensions. We present one such simplification, which results in fewer than 10% as many alignment model parameters and produces results competitive with the original model. An unexpected benefit of this technique is that it naturally gives a measure for how difficult it is to translate from one language to another given a data set. Next, we present one suggestion for adding complexity to model new behavior. en_US
dc.description.statementofresponsibility by Ali Mohammad. en_US
dc.format.extent 53 leaves en_US
dc.format.extent 2283102 bytes
dc.format.extent 2431327 bytes
dc.format.mimetype application/pdf
dc.format.mimetype application/pdf
dc.language.iso eng en_US
dc.publisher Massachusetts Institute of Technology en_US
dc.rights 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. en_US
dc.subject Electrical Engineering and Computer Science. en_US
dc.title Gaussian alignments in statistical translation models en_US
dc.type Thesis en_US S.M. en_US
dc.contributor.department Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science. en_US
dc.identifier.oclc 75292112 en_US

Files in this item

Name Size Format Description
75292112.pdf 2.177Mb PDF Preview, non-printable (open to all)
75292112-MIT.pdf 2.318Mb PDF Full printable version (MIT only)

This item appears in the following Collection(s)

Show simple item record