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

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

Introduction Narratology Computational Narrative Natural Artificial Language Intelligence Processing 2

Motivation Comp. Models New Content & Content of Narrative Experiences PCG & Procedural Narrative Content Generation Systems 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] 3

Authorial Bottleneck Problem • Input required by OPIATE Characters, Locations, Narrative Function Attitudes, … Props, … Sequences Opiate [Fairclough 2007] 4

Motivation Comp. Models of Narrative Story Workbench [Finlayson 2011], Scheherazade [Elson 2012] 5

Motivation Comp. Models Narrative of Narrative Natural Language Processing ProppASM [Finlayson 2011 ], Social Networks [Elson 2010] 6

Motivation Comp. Models New Content & Narrative Content of Narrative Experiences PCG & Natural Procedural Language Narrative Content Processing Generation Systems How can we bridge the “gap” in computational narrative in order to solve the authorial bottleneck problem? 7

Open Problems • “Gap” in Computational Narrative • Authorial bottleneck Comp. Models Content & New Narrative of Narrative Content Experiences PCG & Natural Procedural Narrative Language Content Processing Generation Systems • How to model narrative? 8

Open Problems • “Gap” in Computational Narrative • Authorial bottleneck Comp. Models Content & New Narrative of Narrative Content Experiences PCG & Natural Procedural Narrative Language Content Processing Generation Systems • How to model narrative? • How to adapt and reuse general purpose NLP/IE? 9

Open Problems • “Gap” in Computational Narrative • Authorial bottleneck Comp. Models Content & New Narrative of Narrative Content Experiences PCG & Natural Procedural Narrative Language Content Processing Generation Systems 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

Open Problems • “Gap” in Computational Narrative • Authorial bottleneck Comp. Models Content & New Narrative of Narrative Content Experiences PCG & Natural Procedural Narrative Language Content Processing Generation Systems 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

Conclusions Comp. Models New Content & Narrative Content of Narrative Experiences PCG & Natural Procedural Language Narrative Content Processing Generation Systems 12

Thanks 13

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

Backup Slides 15

Neural all the things! 16

Authorial Bottleneck Problem • Input required by OPIATE Characters, Locations, Narrative Function Attitudes, … Props, … Sequences 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 other side of the woods there was a little town where Sergeant Lip and Corporal Foot lived. They stole the Magic Mirror. [...] Opiate [Fairclough 2007] 17

Authorial Bottleneck Problem • Input required by OPIATE Characters, Locations, Narrative Function Attitudes, … Props, … Sequences 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 other side of the woods there was a little town where Sergeant Lip and Corporal Foot lived. They stole the Magic Mirror. [...] Opiate [Fairclough 2007] 18

Automated Narrative Information Extraction • Voz Mention Coreference Extraction Resolution Natural Language Feature-Vector Character Role Function Preprocessing Assembly Identification Identification Identification Verb Extraction External Domain Examples Examples Knowledge Knowledge 19

Story Graphs 20

Evaluation of IE Pipelines Results Coreference Voting for Roles 21