Bridging the Gap Between Computational Narrative and Natural - - PowerPoint PPT Presentation

▶
bridging the gap between computational narrative and
SMART_READER_LITE
LIVE PREVIEW

Bridging the Gap Between Computational Narrative and Natural - - PowerPoint PPT Presentation

Mar 16, 2024 482 likes •705 views

February 4th 2017 AAAI W17: What's Next for AI in Games? Bridging the Gap Between Computational Narrative and Natural Language Processing Santiago Ontan 1 , Josep Valls-Vargas 1 and Jichen Zhu 2 1 Computer Science, 2 Digital Media Drexel

slide-1
SLIDE 1

Santiago Ontañón1, Josep Valls-Vargas1 and Jichen Zhu2

1Computer Science, 2Digital Media

Drexel University

Bridging the Gap Between Computational Narrative and Natural Language Processing

February 4th 2017 – AAAI W17: What's Next for AI in Games?

slide-2
SLIDE 2

Introduction

Narratology Artificial Intelligence Natural Language Processing

2

Computational Narrative

slide-3
SLIDE 3

Motivation

3

  • Comp. Models
  • f Narrative

New Content Procedural Content Generation

PCG & Narrative Systems Content & Experiences

Joe Bear was hungry. He asked Irving Bird where some honey

  • was. Irving refused to tell him

so Joe offered to bring him a worm if he’d tell him where some honey was. Irving agreed. But Joe didn’t know where any worms were, so he asked Irving, who refused to say.

Tale-spin [Meehan 1976], ASD [Riedl 2011], Opiate [Fairclough 2007]

slide-4
SLIDE 4

Authorial Bottleneck Problem

4

Opiate [Fairclough 2007]

Narrative Function Sequences Characters, Attitudes, … Locations, Props, …

  • Input required by OPIATE
slide-5
SLIDE 5

Motivation

5

  • Comp. Models
  • f Narrative

Story Workbench [Finlayson 2011], Scheherazade [Elson 2012]

slide-6
SLIDE 6

Motivation

6

Narrative

  • Comp. Models
  • f Narrative

Natural Language Processing

ProppASM [Finlayson 2011], Social Networks [Elson 2010]

slide-7
SLIDE 7

Motivation

7

Narrative

  • Comp. Models
  • f Narrative

New Content Natural Language Processing Procedural Content Generation

How can we bridge the “gap” in computational narrative in order to solve the authorial bottleneck problem?

PCG & Narrative Systems Content & Experiences

slide-8
SLIDE 8

Open Problems

  • How to model narrative?

8

  • “Gap” in Computational Narrative
  • Authorial bottleneck

Narrative

  • Comp. Models
  • f Narrative

New Content Natural Language Processing Procedural Content Generation

PCG & Narrative Systems Content & Experiences

slide-9
SLIDE 9

Open Problems

  • How to model narrative?
  • How to adapt and reuse general purpose NLP/IE?

9

  • “Gap” in Computational Narrative
  • Authorial bottleneck

Narrative

  • Comp. Models
  • f Narrative

New Content Natural Language Processing Procedural Content Generation

PCG & Narrative Systems Content & Experiences

slide-10
SLIDE 10

Open Problems

  • How to model narrative?
  • How to adapt and reuse general purpose NLP/IE?
  • How would an author use a NL interface to a CN system?

10

  • “Gap” in Computational Narrative
  • Authorial bottleneck

Narrative

  • Comp. Models
  • f Narrative

New Content Natural Language Processing Procedural Content Generation

PCG & Narrative Systems Content & Experiences

slide-11
SLIDE 11

Open Problems

  • How to model narrative?
  • How to adapt and reuse general purpose NLP/IE?
  • How would an author use a NL interface to a CN system?
  • How to evaluate narrative IE systems?

11

  • “Gap” in Computational Narrative
  • Authorial bottleneck

Narrative

  • Comp. Models
  • f Narrative

New Content Natural Language Processing Procedural Content Generation

PCG & Narrative Systems Content & Experiences

slide-12
SLIDE 12

Conclusions

12

Narrative

  • Comp. Models
  • f Narrative

New Content Natural Language Processing Procedural Content Generation

PCG & Narrative Systems Content & Experiences

slide-13
SLIDE 13

Thanks

13

slide-14
SLIDE 14

Santiago Ontañón1, Josep Valls-Vargas1 and Jichen Zhu2

1Computer Science, 2Digital Media

Drexel University

Bridging the Gap Between Computational Narrative and Natural Language Processing

February 4th 2017 – AAAI W17: What's Next for AI in Games?

slide-15
SLIDE 15

Backup Slides

15

slide-16
SLIDE 16

16

Neural all the things!

slide-17
SLIDE 17

Authorial Bottleneck Problem

17

Opiate [Fairclough 2007]

Narrative Function Sequences Characters, Attitudes, … Locations, Props, …

  • Input required by OPIATE

Once upon a time, Bonji ran into Lili, Mimo and Bibi, three friends who lived in a hut. In a field nearby lived Snomm who had a Magic

  • Mirror. Past the field and further into the woods lived Blobar. In the
  • ther side of the woods there was a little town where Sergeant Lip

and Corporal Foot lived. They stole the Magic Mirror. [...]

slide-18
SLIDE 18

Authorial Bottleneck Problem

18

Opiate [Fairclough 2007]

Narrative Function Sequences Characters, Attitudes, … Locations, Props, …

  • Input required by OPIATE

Once upon a time, Bonji ran into Lili, Mimo and Bibi, three friends who lived in a hut. In a field nearby lived Snomm who had a Magic

  • Mirror. Past the field and further into the woods lived Blobar. In the
  • ther side of the woods there was a little town where Sergeant Lip

and Corporal Foot lived. They stole the Magic Mirror. [...]

slide-19
SLIDE 19

Verb Extraction Mention Extraction Feature-Vector Assembly Role Identification Coreference Resolution Character Identification

External Knowledge Examples Examples

Function Identification

Domain Knowledge

Natural Language Preprocessing

Automated Narrative Information Extraction

  • Voz

19

slide-20
SLIDE 20

Story Graphs

20

slide-21
SLIDE 21

Evaluation of IE Pipelines

Results

21

Coreference Voting for Roles