HOMER: A Creative Story Generation System Student: Dimitrios N. Konstantinou Supervisor: Prof. Paul Mc Kevitt School of Computing and Intelligent Systems Faculty of Informatics University of Ulster, Magee

1
HOMER A Creative Story Generation System
Student Dimitrios N. KonstantinouSupervisor
Prof. Paul Mc KevittSchool of Computing and
Intelligent Systems Faculty of
InformaticsUniversity of Ulster, Magee
2
Objectives of HOMER

• To build a creative storytelling agent
• that generates
• style-constrained stories
• stories with a point of view
• natural language output
• domain-independent stories

3
Literature Review

• Creativity Systems
• Copycat
• Genesis
• Letter Spirit
• A Computational Model of Music
• A Computational Model of Poetry

4

• Schanks Theory of CD, Scripts, and Stories
• A Robotic Storyteller
• An objection to Schanks Theory
• Scripts and Point of View
• Story Grammars

5
Comparison with other storytelling systems
6
The Rationale for HOMER

• Approximate the creative conceptual space in
• human narratives
• Transform the conceptual space
• Build domain-independence
• Develop an extendable creative agent
• Simulate author goals

7
Motivation

• Create associative clusters of variables
• (archetypical modes)
• Simulate high-level style decisions in story
  output
• Introduce mid- / low-level style decisions
• Simulate point of view
• Create lexical entries and use transformational
  
• procedures

8
The Parser

• Input
  frame

Language Understander
Inference Mechanism
Frame Constructor
Style Specifier
9
The Story-outline Constructor

• Frame
  story-outline

Mode-based imagery
Mode-based Hierarchies
10
The Natural Language Generator

• Story
  narrative
• outline

Text Planner
Narrative Reasoner
Ontology
Narrative History
Surface Realizer
Revisor
11
Conclusion

• HOMER a creative storytelling agent that
• takes as input a story fragment, style
  specifications and contextual clues
• simulates authorial creative goals
• generates narrative in the form of natural
  language output
• approximates human language output

12
Software Tools Analysis

• Parsing
• Attribute Logic Engine (ALE 3.2)
• Lexical Knowledge Base (LKB)
• Rhetorical Structure Tool (RST)
• Natural Language Generation
• Upper Model from KPML
• Systemic Unification Realization Grammar of
  English
• (SURGE)
• I-SAURUS, lexicon for near-synonyms

13
Storytelling Systems

• Structure-based Vs. Environment-based
• Automatic Novel Writer (1973) ? HOMER (2004)
• AESOPWORLD(1996)? Larsen Petersen (1999)
• Story elements story-line, plot, setting,
• style, point of view
• Story Understanding
• Creativity

14
Project plan
15
Architecture of HOMER
Thematic Memory

• Input
  
  output

Parser
Story-Outline Constructor
Natural Language Generator