Paper Presentation: A Survey on Story Generation Techniques

This talk presents the findings of Kybartas and Bidarra in their survey paper on story generation techniques:
https://graphics.tudelft.nl/Publications-new/2016/KB16/Survey.pdf

Transcript

1. A Survey on Story Generation
   Techniques
   for Authoring Computational
   Narratives
   Paper by Ben Kybartas and Rafael Bidarra
   Presentation by Chris Martens
   CSC 791: Generative Methods
   Monday, October 24, 2016
   1
   

   View Slide

2. Purpose of this paper
   2
   Q: What is the purpose of any survey paper?
   

   View Slide

3. Purpose of this paper
   3
   Define common goals of a research community
   Review progress on those goals
   Classify progress along different axes
   Identify gaps for future work
   

   View Slide

4. Human-Computer
   Collaboration
   4
   Which parts does the computer do?
   Which parts does the human do?
   

   View Slide

5. Outline
   5
   Terminology
   Examples
   Classification Scheme
   Examples to Test
   

   View Slide

6. Terminology
   6
   

   View Slide

7. View Slide

8. View Slide

9. View Slide

10. Story vs. Space
    10
    Playwright vs. Director
    script:
    characters
    act structure
    scenes
    lines
    performance:
    actors
    props
    set
    delivery
    

    View Slide

11. View Slide

12. Plot Automation
    12
    Manual
    Structure
    Template
    Constrained
    Automated
    

    View Slide

13. Plot Automation
    13
    Manual
    Structure
    Template
    Constrained
    Automated
    Computer is
    present at a mostly
    invisible level
    

    View Slide

14. Plot Automation
    14
    Manual
    Structure
    Template
    Constrained
    Automated
    Computer is
    present at a mostly
    invisible level
    Attempts to
    minimize author
    involvement as
    much as possible
    

    View Slide

15. 15
    Examples
    

    View Slide

16. 16
    Manual Authoring Tools
    Interactive Fiction Creation
    Programming Education
    Therapy
    

    View Slide

17. 17
    Storyspace
    Twine
    Inform 7
    

    View Slide

18. Scrivener
    18
    

    View Slide

19. 19
    Plot Generation Systems
    Grammar-based
    Planning-based
    Other
    

    View Slide

20. Grammars as Templates
    20
    Grammar describes an outline of the narrative
    but does not populate it with existents.
    

    View Slide

21. Proppian Grammars
    21
    

    View Slide

22. Cohn Comic Grammars
    22
    

    View Slide

23. Grammars as Complete Plot
    Generators
    23
    GESTER: rules defining relations between
    existents
    TEATRIX: grammar as director, player as
    performer
    

    View Slide

24. Grammars as Complete Plot
    Generators
    24
    GESTER
    

    View Slide

25. ReGen: Story Graph Rewriting
    25
    

    View Slide

26. Planning-Based Systems
    26
    Story Canvas
    

    View Slide

27. Porteous et al.
    “Applying planning to interactive storytelling”
    27
    

    View Slide

28. Case-Based Reasoning
    28
    Engage/Reflect Cycle
    Reflection uses a corpus of previous stories to
    evaluate and revise the current story on the basis
    of novelty.
    MEXICA
    

    View Slide

29. Social Physics Engines
    29
    Prom Week
    

    View Slide

30. Social
    Physics
    Engines
    30
    Versu
    

    View Slide

31. 31
    Space Generation Systems
    

    View Slide

32. Text-to-Image Systems
    32
    

    View Slide

33. 33
    Skyrim Radiant Quests
    

    View Slide

34. 34
    GameForge: As seen in the PCG Book
    Story as input
    Valid space as output
    

    View Slide

35. 35
    Complete Story
    Generation Systems
    

    View Slide

36. 36
    Fabulist
    Initial State Revision
    Example: location of a hidden weapon needed
    for stealthy assassination
    

    View Slide

37. 37
    Generating space on the fly
    Virtual Storyteller: Late commitment
    Inspired by improvisational theater
    Example: Character want to fight each
    other? Spawn some weapons
    Similarly,
    Li and Riedl: Gadget generation
    

    View Slide

38. 38
    Scheherezade
    Crowd-sourced story choices
    

    View Slide

39. 39
    Universe
    Generating backstories for characters with family
    tree simulation
    Temporal coherence: if plot requires two
    characters to fall in love, their birthdates must be
    within a reasonable range of one another
    

    View Slide

40. 40
    Dwarf Fortress
    “Emergent Storytelling”
    

    View Slide

41. 41
    Classification Scheme
    

    View Slide

42. Plot Automation
    42
    Manual
    Structure
    Template
    Constrained
    Automated
    

    View Slide

43. Plot Automation
    43
    Structure
    Computer provides plot structure,
    but no specific events or event
    orderings.
    e.g. Scrivener
    

    View Slide

44. Plot Automation
    44
    Template
    Computer provides plot template with events in order, but
    instantiation with existents is left to the human author.
    e.g. Propp grammars
    

    View Slide

45. Plot Automation
    45
    Constrained
    Author provides initial state or other narrative constraints;
    computer gives complete plot populated with existents.
    e.g. GME, Mexica, Prom Week
    

    View Slide

46. Space Automation
    46
    Manual
    Modification
    Simulation
    Constrained
    Automated
    

    View Slide

47. Space Automation
    47
    Modification
    Author provides a starting point, but the computer
    can modify it, e.g. to suit the plot structure.
    e.g.: initial state revision; late commitment
    

    View Slide

48. Space Automation
    48
    Simulation
    New spatial content is generated by simulating
    interactions between hand-authored existents,
    resulting in an initial state for story.
    e.g.: Universe’s family tree generation
    

    View Slide

49. Space Automation
    49
    Constrained
    New spatial content is generated to satisfy authored
    constraints.
    e.g.: Dwarf Fortress
    

    View Slide

50. View Slide

51. View Slide

52. 52
    Examples to test
    classification
    

    View Slide

53. View Slide

54. Ice-Bound
    54
    

    View Slide

55. Epitaph
    55
    https://mkremins.itch.io/epitaph
    

    View Slide