dc.contributor.advisor | Patrick H. Winston. | en_US |
dc.contributor.author | Noss, Jessica Marie. | en_US |
dc.contributor.other | Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science. | en_US |
dc.date.accessioned | 2018-01-12T21:15:33Z | |
dc.date.available | 2018-01-12T21:15:33Z | |
dc.date.copyright | 2017 | en_US |
dc.date.issued | 2017 | en_US |
dc.identifier.uri | http://hdl.handle.net/1721.1/113174 | en_US |
dc.description | Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2017 | en_US |
dc.description | Cataloged from PDF version of thesis. | en_US |
dc.description | Includes bibliographical references (page 63). | en_US |
dc.description.abstract | Stories are essential to human communication, thus understanding stories is critical to modeling human intelligence. In order to understand a story from multiple characters' perspectives, a reader must form mental models representing each character's knowledge and beliefs. Building on the Genesis story-understanding system, I developed the Perspectives Expert, which enables Genesis to form detailed mental models of characters in a story. I started by annotating stories with characters' entrances and exits, treating stories as theatrical plays. I assumed that characters observe events only while onstage, and I used their observations to populate mental models. Then, inspired by human reasoning, I eliminated explicit stage directions and enabled Genesis to keep track of characters' locations and levels of consciousness. Equipped with this mental-modeling ability, Genesis can retell stories from different characters' perspectives, answer reading-comprehension questions to demonstrate understanding, and perform the first steps of conflict reconciliation by detecting and explaining opposing viewpoints. | en_US |
dc.description.statementofresponsibility | by Jessica Marie Noss. | en_US |
dc.format.extent | 63 pages | en_US |
dc.language.iso | eng | en_US |
dc.publisher | Massachusetts Institute of Technology | en_US |
dc.rights | MIT theses are protected by copyright. They may be viewed, downloaded, or printed from this source but further reproduction or distribution in any format is prohibited without written permission. | en_US |
dc.rights.uri | http://dspace.mit.edu/handle/1721.1/7582 | en_US |
dc.subject | Electrical Engineering and Computer Science. | en_US |
dc.title | Who knows what? : perspective-enabled story understanding | en_US |
dc.title.alternative | Perspective-enabled story understanding | en_US |
dc.type | Thesis | en_US |
dc.description.degree | M. Eng. | en_US |
dc.contributor.department | Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science | en_US |
dc.identifier.oclc | 1017490236 | en_US |
dc.description.collection | M.Eng. Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science | en_US |
dspace.imported | 2019-06-17T20:36:17Z | en_US |