MIT Libraries logoDSpace@MIT

MIT
View Item 
  • DSpace@MIT Home
  • MIT Libraries
  • MIT Theses
  • Doctoral Theses
  • View Item
  • DSpace@MIT Home
  • MIT Libraries
  • MIT Theses
  • Doctoral Theses
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

CoMo : a whiteboard that converses about code

Author(s)
Sabisch, Andrew Thomas Correa
Thumbnail
DownloadFull printable version (7.361Mb)
Other Contributors
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science.
Advisor
Randall Davis.
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
Software engineers routinely solve problems by brainstorming at whiteboards. Among other modes, they communicate with speech and sketch. Unfortunately, the whiteboard plays the role of a passive medium. It serves only as a place to draw. But what if it could engage in the conversation, even to a limited degree? Ideally it would help guide the engineers to a solution by being an active participant in the conversation. This thesis presents an early version of that vision: CoMo, a whiteboard that converses about code. CoMo is capable of engaging its user in a constrained mixed-initiative symmetric-multimodal conversation about a data structure manipulation. When it understands the data structure, it uses a code synthesis system to generate functioning C code. It can successfully hold a limited conversation and synthesize code for 50 manipulations on 8 data structures. This thesis further presents findings from an observational user study that helped guide the interaction with CoMo. Finally, this thesis presents the mixed-initiative code-generation framework that CoMo implements to achieve its interaction, and the insights about having limited natural conversations about data structure manipulations that were gleaned while creating the framework.
Description
Thesis: Sc. D., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2014.
 
This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections.
 
Cataloged from student-submitted PDF version of thesis.
 
Includes bibliographical references (pages 181-184).
 
Date issued
2014
URI
http://hdl.handle.net/1721.1/93777
Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Publisher
Massachusetts Institute of Technology
Keywords
Electrical Engineering and Computer Science.

Collections
  • Doctoral Theses

Browse

All of DSpaceCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

My Account

Login

Statistics

OA StatisticsStatistics by CountryStatistics by Department
MIT Libraries
PrivacyPermissionsAccessibilityContact us
MIT
Content created by the MIT Libraries, CC BY-NC unless otherwise noted. Notify us about copyright concerns.