Generate Believable Causal Plots with User Preferences Using Constrained Monte Carlo Tree Search

Von Wun Soo; Chi Mou Lee; Tai Hsun Chen

Generate Believable Causal Plots with User Preferences Using Constrained Monte Carlo Tree Search

Von Wun Soo
, Chi Mou Lee
, Tai Hsun Chen

National Tsing Hua University

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

6 Scopus citations

Abstract

We construct a large scale of causal knowledge in term of Fabula elements by extracting causal links from existing common sense ontology ConceptNet5. We design a Constrained Monte Carlo Tree Search (cMCTS) algorithm that allows users to specify positive and negative concepts to appear in the generated stories. cMCTS can find a believable causal story plot. We show the merits by experiments and discuss the remedy strategies in cMCTS that may generate incoherent causal plots.

Original language	English
Title of host publication	Proceedings of the 12th AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, AIIDE 2016
Editors	Nathan Sturtevant, Brian Magerko
Publisher	Association for the Advancement of Artificial Intelligence
Pages	218-224
Number of pages	7
ISBN (Electronic)	9781577357728
State	Published - 08 10 2016
Externally published	Yes
Event	12th Annual AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, AIIDE 2016 - Burlingame, United States Duration: 08 10 2016 → 12 10 2016

Publication series

Name	Proceedings - AAAI Artificial Intelligence and Interactive Digital Entertainment Conference, AIIDE
ISSN (Print)	2326-909X
ISSN (Electronic)	2334-0924

Conference

Conference	12th Annual AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, AIIDE 2016
Country/Territory	United States
City	Burlingame
Period	08/10/16 → 12/10/16

Bibliographical note

Publisher Copyright:
Copyright © 2016, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.

Keywords

believable story generation
causal story plots
constrained Monte Carlo Tree Search
Fabula elements
user preference

Cite this

Soo, V. W., Lee, C. M., & Chen, T. H. (2016). Generate Believable Causal Plots with User Preferences Using Constrained Monte Carlo Tree Search. In N. Sturtevant, & B. Magerko (Eds.), Proceedings of the 12th AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, AIIDE 2016 (pp. 218-224). (Proceedings - AAAI Artificial Intelligence and Interactive Digital Entertainment Conference, AIIDE). Association for the Advancement of Artificial Intelligence.

Soo, Von Wun ; Lee, Chi Mou ; Chen, Tai Hsun. / Generate Believable Causal Plots with User Preferences Using Constrained Monte Carlo Tree Search. Proceedings of the 12th AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, AIIDE 2016. editor / Nathan Sturtevant ; Brian Magerko. Association for the Advancement of Artificial Intelligence, 2016. pp. 218-224 (Proceedings - AAAI Artificial Intelligence and Interactive Digital Entertainment Conference, AIIDE).

@inproceedings{5326383f9d874b2cbc9865aaf1dca4e2,

title = "Generate Believable Causal Plots with User Preferences Using Constrained Monte Carlo Tree Search",

abstract = "We construct a large scale of causal knowledge in term of Fabula elements by extracting causal links from existing common sense ontology ConceptNet5. We design a Constrained Monte Carlo Tree Search (cMCTS) algorithm that allows users to specify positive and negative concepts to appear in the generated stories. cMCTS can find a believable causal story plot. We show the merits by experiments and discuss the remedy strategies in cMCTS that may generate incoherent causal plots.",

keywords = "believable story generation, causal story plots, constrained Monte Carlo Tree Search, Fabula elements, user preference",

author = "Soo, \{Von Wun\} and Lee, \{Chi Mou\} and Chen, \{Tai Hsun\}",

note = "Publisher Copyright: Copyright {\textcopyright} 2016, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.; 12th Annual AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, AIIDE 2016 ; Conference date: 08-10-2016 Through 12-10-2016",

year = "2016",

month = oct,

day = "8",

language = "英语",

series = "Proceedings - AAAI Artificial Intelligence and Interactive Digital Entertainment Conference, AIIDE",

publisher = "Association for the Advancement of Artificial Intelligence",

pages = "218--224",

editor = "Nathan Sturtevant and Brian Magerko",

booktitle = "Proceedings of the 12th AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, AIIDE 2016",

address = "美国",

}

Soo, VW, Lee, CM & Chen, TH 2016, Generate Believable Causal Plots with User Preferences Using Constrained Monte Carlo Tree Search. in N Sturtevant & B Magerko (eds), Proceedings of the 12th AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, AIIDE 2016. Proceedings - AAAI Artificial Intelligence and Interactive Digital Entertainment Conference, AIIDE, Association for the Advancement of Artificial Intelligence, pp. 218-224, 12th Annual AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, AIIDE 2016, Burlingame, United States, 08/10/16.

Generate Believable Causal Plots with User Preferences Using Constrained Monte Carlo Tree Search. / Soo, Von Wun; Lee, Chi Mou; Chen, Tai Hsun.
Proceedings of the 12th AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, AIIDE 2016. ed. / Nathan Sturtevant; Brian Magerko. Association for the Advancement of Artificial Intelligence, 2016. p. 218-224 (Proceedings - AAAI Artificial Intelligence and Interactive Digital Entertainment Conference, AIIDE).

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

TY - GEN

T1 - Generate Believable Causal Plots with User Preferences Using Constrained Monte Carlo Tree Search

AU - Soo, Von Wun

AU - Lee, Chi Mou

AU - Chen, Tai Hsun

PY - 2016/10/8

Y1 - 2016/10/8

N2 - We construct a large scale of causal knowledge in term of Fabula elements by extracting causal links from existing common sense ontology ConceptNet5. We design a Constrained Monte Carlo Tree Search (cMCTS) algorithm that allows users to specify positive and negative concepts to appear in the generated stories. cMCTS can find a believable causal story plot. We show the merits by experiments and discuss the remedy strategies in cMCTS that may generate incoherent causal plots.

AB - We construct a large scale of causal knowledge in term of Fabula elements by extracting causal links from existing common sense ontology ConceptNet5. We design a Constrained Monte Carlo Tree Search (cMCTS) algorithm that allows users to specify positive and negative concepts to appear in the generated stories. cMCTS can find a believable causal story plot. We show the merits by experiments and discuss the remedy strategies in cMCTS that may generate incoherent causal plots.

KW - believable story generation

KW - causal story plots

KW - constrained Monte Carlo Tree Search

KW - Fabula elements

KW - user preference

UR - https://www.scopus.com/pages/publications/85079040562

M3 - 会议稿件

AN - SCOPUS:85079040562

T3 - Proceedings - AAAI Artificial Intelligence and Interactive Digital Entertainment Conference, AIIDE

SP - 218

EP - 224

BT - Proceedings of the 12th AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, AIIDE 2016

A2 - Sturtevant, Nathan

A2 - Magerko, Brian

PB - Association for the Advancement of Artificial Intelligence

T2 - 12th Annual AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, AIIDE 2016

Y2 - 8 October 2016 through 12 October 2016

ER -

Soo VW, Lee CM, Chen TH. Generate Believable Causal Plots with User Preferences Using Constrained Monte Carlo Tree Search. In Sturtevant N, Magerko B, editors, Proceedings of the 12th AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, AIIDE 2016. Association for the Advancement of Artificial Intelligence. 2016. p. 218-224. (Proceedings - AAAI Artificial Intelligence and Interactive Digital Entertainment Conference, AIIDE).

Generate Believable Causal Plots with User Preferences Using Constrained Monte Carlo Tree Search

Abstract

Publication series

Conference

Bibliographical note

Keywords

Other files and links

Fingerprint

Cite this