Login

The Strong Story Hypothesis and the Directed Perception Hypothesis

Show full item record




Title: The Strong Story Hypothesis and the Directed Perception Hypothesis
Author: Winston, Patrick Henry
Department: Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science
Publisher: Association for the Advancement of Artificial Intelligence
Issue Date: 2011-11
Abstract: I ask why humans are smarter than other primates, and I hypothesize that an important part of the answer lies in what I call the Strong Story Hypothesis, which holds that story telling and understanding have a central role in human intelligence. Next, I introduce another hypothesis, the Driven Perception Hypothesis, which holds that we derive much of our commonsense, including the commonsense required in story understanding, by deploying our perceptual apparatus on real and imagined events. Then, after discussing methodology, I describe the representations and methods embodied in the Genesis system, a story-understanding system that analyzes stories ranging from precis of Shakespeare's plots to descriptions of conflicts in cyberspace. The Genesis system works with short story summaries, provided in English, together with low-level commonsense rules and higher-level reflection patterns, likewise expressed in English. Using only a small collection of commonsense rules and reflection patterns, Genesis demonstrates several story-understanding capabilities, such as determining that both Macbeth and the 2007 Russia-Estonia Cyberwar involve revenge, even though neither the word revenge nor any of its synonyms are mentioned. Finally, I describe Rao's Visio-Spatial Reasoning System, a system that recognizes activities such as approaching, jumping, and giving, and answers commonsense questions posed by Genesis.
URI: http://hdl.handle.net/1721.1/67693
Citation: Winston, Patrick. "The Strong Story Hypothesis and the Directed Perception Hypothesis" AAAI Fall Symposium Series (2011): n. pag. Web. 15 Dec. 2011 © 2011 Association for the Advancement of Artificial Intelligence
Version: Author's final manuscript
Terms of Use: Creative Commons Attribution-Noncommercial-Share Alike 3.0
Detailed Terms: http://creativecommons.org/licenses/by-nc-sa/3.0/
Published as: http://www.aaai.org/ocs/index.php/FSS/FSS11/paper/view/4125/4534
Journal: Proceedings of the AAAI Fall Symposium on Advances in Cognitive Systems

Files in this item

Files Size Format
Downloadable Full Text - application/pdf

This item appears in the following Collection(s)

Show full item record

Creative Commons Attribution-Noncommercial-Share Alike 3.0 Except where otherwise noted, this item's license is described as Creative Commons Attribution-Noncommercial-Share Alike 3.0

Search DSpace@MIT


Advanced Search

Browse

My Account

Links