Guided open story generation using probabilistic graphical models

Sagar Gandhi; Brent Harrison

doi:10.1145/3337722.3341871

Guided open story generation using probabilistic graphical models

Sagar Gandhi, Brent Harrison

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

In this work, we present an approach for performing computational storytelling in open domain based on Author Goals. Author Goals are constraints placed on a story event directed by the author of the system. There are two challenges present in this type of story generation: (1) automatically acquiring a model of story progression, and (2) guiding the progress of story progression in light of different goals. We propose a novel approach to story generation based on probabilistic graphical models and Loopy Belief Propagation (LBP) that addresses both of these problems. We show the applicability of our technique through a case study on the Visual Storytelling (VIST) 2017 dataset. We use image descriptions as author goals. This empirical analysis suggests that our approach is able to utilize goals information to better automatically generate stories.

Original language	English
Title of host publication	Proceedings of the 14th International Conference on the Foundations of Digital Games, FDG 2019
Editors	Foaad Khosmood, Johanna Pirker, Thomas Apperley, Sebastian Deterding
ISBN (Electronic)	9781450372176
DOIs	https://doi.org/10.1145/3337722.3341871
State	Published - Aug 26 2019
Event	14th International Conference on the Foundations of Digital Games, FDG 2019 - San Luis Obispo, United States Duration: Aug 26 2019 → Aug 30 2019

Publication series

Name	ACM International Conference Proceeding Series

Conference

Conference	14th International Conference on the Foundations of Digital Games, FDG 2019
Country/Territory	United States
City	San Luis Obispo
Period	8/26/19 → 8/30/19

Bibliographical note

Publisher Copyright:
© 2019 ACM.

Keywords

Belief propagation
Computational storytelling
Natural language generation
Probabilistic graphical models

ASJC Scopus subject areas

Software
Human-Computer Interaction
Computer Vision and Pattern Recognition
Computer Networks and Communications

Access to Document

10.1145/3337722.3341871

Cite this

@inproceedings{16c42f3000e84856b1e79d8b018544fc,

title = "Guided open story generation using probabilistic graphical models",

abstract = "In this work, we present an approach for performing computational storytelling in open domain based on Author Goals. Author Goals are constraints placed on a story event directed by the author of the system. There are two challenges present in this type of story generation: (1) automatically acquiring a model of story progression, and (2) guiding the progress of story progression in light of different goals. We propose a novel approach to story generation based on probabilistic graphical models and Loopy Belief Propagation (LBP) that addresses both of these problems. We show the applicability of our technique through a case study on the Visual Storytelling (VIST) 2017 dataset. We use image descriptions as author goals. This empirical analysis suggests that our approach is able to utilize goals information to better automatically generate stories.",

keywords = "Belief propagation, Computational storytelling, Natural language generation, Probabilistic graphical models",

author = "Sagar Gandhi and Brent Harrison",

note = "Publisher Copyright: {\textcopyright} 2019 ACM.; 14th International Conference on the Foundations of Digital Games, FDG 2019 ; Conference date: 26-08-2019 Through 30-08-2019",

year = "2019",

month = aug,

day = "26",

doi = "10.1145/3337722.3341871",

language = "English",

series = "ACM International Conference Proceeding Series",

editor = "Foaad Khosmood and Johanna Pirker and Thomas Apperley and Sebastian Deterding",

booktitle = "Proceedings of the 14th International Conference on the Foundations of Digital Games, FDG 2019",

}

Gandhi, S & Harrison, B 2019, Guided open story generation using probabilistic graphical models. in F Khosmood, J Pirker, T Apperley & S Deterding (eds), Proceedings of the 14th International Conference on the Foundations of Digital Games, FDG 2019., 79, ACM International Conference Proceeding Series, 14th International Conference on the Foundations of Digital Games, FDG 2019, San Luis Obispo, United States, 8/26/19. https://doi.org/10.1145/3337722.3341871

Guided open story generation using probabilistic graphical models. / Gandhi, Sagar; Harrison, Brent.
Proceedings of the 14th International Conference on the Foundations of Digital Games, FDG 2019. ed. / Foaad Khosmood; Johanna Pirker; Thomas Apperley; Sebastian Deterding. 2019. 79 (ACM International Conference Proceeding Series).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Guided open story generation using probabilistic graphical models

AU - Gandhi, Sagar

AU - Harrison, Brent

PY - 2019/8/26

Y1 - 2019/8/26

N2 - In this work, we present an approach for performing computational storytelling in open domain based on Author Goals. Author Goals are constraints placed on a story event directed by the author of the system. There are two challenges present in this type of story generation: (1) automatically acquiring a model of story progression, and (2) guiding the progress of story progression in light of different goals. We propose a novel approach to story generation based on probabilistic graphical models and Loopy Belief Propagation (LBP) that addresses both of these problems. We show the applicability of our technique through a case study on the Visual Storytelling (VIST) 2017 dataset. We use image descriptions as author goals. This empirical analysis suggests that our approach is able to utilize goals information to better automatically generate stories.

AB - In this work, we present an approach for performing computational storytelling in open domain based on Author Goals. Author Goals are constraints placed on a story event directed by the author of the system. There are two challenges present in this type of story generation: (1) automatically acquiring a model of story progression, and (2) guiding the progress of story progression in light of different goals. We propose a novel approach to story generation based on probabilistic graphical models and Loopy Belief Propagation (LBP) that addresses both of these problems. We show the applicability of our technique through a case study on the Visual Storytelling (VIST) 2017 dataset. We use image descriptions as author goals. This empirical analysis suggests that our approach is able to utilize goals information to better automatically generate stories.

KW - Belief propagation

KW - Computational storytelling

KW - Natural language generation

KW - Probabilistic graphical models

UR - http://www.scopus.com/inward/record.url?scp=85072821194&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85072821194&partnerID=8YFLogxK

U2 - 10.1145/3337722.3341871

DO - 10.1145/3337722.3341871

M3 - Conference contribution

AN - SCOPUS:85072821194

T3 - ACM International Conference Proceeding Series

BT - Proceedings of the 14th International Conference on the Foundations of Digital Games, FDG 2019

A2 - Khosmood, Foaad

A2 - Pirker, Johanna

A2 - Apperley, Thomas

A2 - Deterding, Sebastian

T2 - 14th International Conference on the Foundations of Digital Games, FDG 2019

Y2 - 26 August 2019 through 30 August 2019

ER -

Guided open story generation using probabilistic graphical models

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this