2026-09-19T03:03:40Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/1015722026-06-16T18:55:00Zcom_1721.1_7582com_1721.1_7581col_1721.1_131022
Kushman, Nate
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science.
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
2016-03-03T21:09:47Z
2016-03-03T21:09:47Z
2015
2015
http://hdl.handle.net/1721.1/101572
940573214
Thesis: Ph. D., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2015.
Cataloged from PDF version of thesis.
Includes bibliographical references (pages 159-169).
This thesis addresses the problem of learning to translate natural language into preexisting programming languages supported by widely-deployed computer systems. Generating programs for existing computer systems enables us to take advantage of two important capabilities of these systems: computing the semantic equivalence between programs, and executing the programs to obtain a result. We present probabilistic models and inference algorithms which integrate these capabilities into the learning process. We use these to build systems that learn to generate programs from natural language in three different computing domains: text processing, solving math problems, and performing robotic tasks in a virtual world. In all cases the resulting systems provide significant performance gains over strong baselines which do not exploit the underlying system capabilities to help interpret the text.
by Nate Kushman.
Ph.D.
169 pages
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.
Generating computer programs from natural language descriptions
Thesis
application/pdf
false
Publication
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="47fa4dc6-e72a-4764-96ed-0db7c9ac1336">
<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>Generating computer programs from natural language descriptions</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2015</PublicationDate>
<Authors>
<Author>
<DisplayName>Kushman, Nate</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>This thesis addresses the problem of learning to translate natural language into preexisting programming languages supported by widely-deployed computer systems. Generating programs for existing computer systems enables us to take advantage of two important capabilities of these systems: computing the semantic equivalence between programs, and executing the programs to obtain a result. We present probabilistic models and inference algorithms which integrate these capabilities into the learning process. We use these to build systems that learn to generate programs from natural language in three different computing domains: text processing, solving math problems, and performing robotic tasks in a virtual world. In all cases the resulting systems provide significant performance gains over strong baselines which do not exploit the underlying system capabilities to help interpret the text.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>