Collecting Grist for the Analogical Mill

1
Collecting Grist for the Analogical Mill

• Patrick H. Winston
• Ford Professor of Artificial Intelligence and
  Computer Science

2
Cultural Prediction Blunder Stopping

• Stories capture cultural beliefs values
• Folktales, Myths, Morality Tales, Religious
  Texts, Urban Legends
• Analogical Framework
• Predict role-models individual group
  behavioracross cultures from stories
• Story Database
• A bottleneck

Automatic NLP
Textual Materials
Structured Representations
Experimenter
3
The Story Workbench

• Modular
• Easily Extendible
• Cross-Platform (99 pure Java)
• Open Source
• Large, dedicated User-base
• Commercial-Quality

4
A Rich Suite of Representations
Where we are going
Listening on the Radio to

• Context
• (last game of the World Series)
• Location
• (pitcher is on the mound, baseman and crowd are
  in front of the pitcher)
• Events (and their order)
• (The look, the windup, then the pitch)
• Causality
• (pitchers pitch causes the ball to fly forward)
• Discourse
• (pitcher is rumored to have taken steroids, hes
  quoted as denying it)
• Emotions
• (The pitcher is calm, the crowd is going wild)
• Motivations
• (The pitcher wants to win the game, wants to
  strike out this batter)

Classical
5
Accomplishments to Date

• Implemented Story Workbench foundation
• Syntax-level NLP representations parsers
• Facility for user correction
• Interfaced successfully with Forbus Group
• Ability to assign CYC propositions to text
  (semantic interpretation)
• Started beta testing
• Word Sense Disambiguation as a benchmark semantic
  annotation task
• Annotation of Discourse structure by Gibson
  Kraemer at MIT BCS

6
Activities in the Near-term

• Implement next layers of representation and
  parsers
• Entities
• Events
• Discourse Relations
• Mental States and Motivations
• Moral of the Story
• Collaborate with Medin at Northwestern to infer
  beliefs from stories and predict Menominee and
  Itza behavior