2026-09-18T23:55:47Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/456352022-01-13T07:54:29Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
Michael Collins.
Lieberman, Michael (Michael R.)
Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science.
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
2009-06-25T20:36:52Z
2009-06-25T20:36:52Z
2008
2008
http://hdl.handle.net/1721.1/45635
367589686
Thesis (M. Eng.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2008.
This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections.
Includes bibliographical references (p. 39-40).
We present a novel approach to multi-engine machine translation, using a feature-based classification algorithm. Instead of just using language models, translation models, or internal confidence scores, we sought out other features that could be used to determine which of two translations to select. We combined the outputs from a phrase-based system, Moses [Koehn et al., 2007] and a tree-to-tree system [Cowan et al., 2006]. Our main result is a 0.3 to 0.4 improvement in BLEU score over the best single system used, while also improving fluency and adequacy judgments. In addition, we used the same setup to directly predict which sentences would be judged by humans to be more fluent and more adequate. In those domains, we predicted the better sentence 6% to 7% more often than a baseline of always choosing the single best system.
by Michael Lieberman.
M.Eng.
40 p.
eng
Massachusetts Institute of Technology
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
Electrical Engineering and Computer Science.
Combining phrase-based and tree-to-tree translation
Thesis
application/pdf
false
Publication
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="16589c90-dada-4722-97b7-fd66f41d205f">
<Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type>
<Language>eng</Language>
<Title>Combining phrase-based and tree-to-tree translation</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2008</PublicationDate>
<Authors>
<Author>
<DisplayName>Lieberman, Michael (Michael R.)</DisplayName>
<Affiliation>
<OrgUnit>
</OrgUnit>
</Affiliation>
</Author>
</Authors>
<Editors>
</Editors>
<Publishers>
<Publisher>
<DisplayName>Massachusetts Institute of Technology</DisplayName>
<OrgUnit />
</Publisher>
</Publishers>
<License>http://dspace.mit.edu/handle/1721.1/7582</License>
<Keyword>Electrical Engineering and Computer Science.</Keyword>
<Abstract>We present a novel approach to multi-engine machine translation, using a feature-based classification algorithm. Instead of just using language models, translation models, or internal confidence scores, we sought out other features that could be used to determine which of two translations to select. We combined the outputs from a phrase-based system, Moses [Koehn et al., 2007] and a tree-to-tree system [Cowan et al., 2006]. Our main result is a 0.3 to 0.4 improvement in BLEU score over the best single system used, while also improving fluency and adequacy judgments. In addition, we used the same setup to directly predict which sentences would be judged by humans to be more fluent and more adequate. In those domains, we predicted the better sentence 6% to 7% more often than a baseline of always choosing the single best system.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>