Automated Extension of Narrative Planning Domains with Antonymic Operators

Julie Porteous, Alan Lindsay, Jonathon Read, Mark Truran, Marc Cavazza

Research output: Chapter in Book/Report/Conference proceedingConference contribution

8 Citations (Scopus)

Abstract

AI Planning has been widely used for narrative generation and the control of virtual actors in interactive storytelling. Planning models for such dynamic environments must include alternative actions which enable deviation away from a baseline storyline in order to generate multiple story variants and to be able to respond to changes that might be made to the story world. However, the actual creation of these domain models has been a largely empirical process with a lack of principled approaches to the definition of alternative actions. Our work has addressed this problem and in the paper we present a novel automated method for the generation of interactive narrative domain models from existing non-interactive versions. Central to this is the use of actions that are contrary to those forming the baseline plot within a principled mechanism for their semi-automatic production. It is important that such newly created domain content should still be human-readable and to this end labels for new actions and predicates are generated automatically using antonyms selected from a range of on-line lexical resources. Our approach is fully implemented in a prototype system and its potential demonstrated via both formal experimental evaluation and user evaluation of the generated action labels.
Original languageEnglish
Title of host publicationAAMAS '15
Subtitle of host publicationProceedings of the 2015 International Conference on Autonomous Agents and Multiagent Systems
PublisherAssociation for Computing Machinery (ACM)
Pages1547-1555
Number of pages9
ISBN (Electronic)9781450334136
Publication statusPublished - 4 May 2015
Externally publishedYes
Event14th International Conference on Autonomous Agents and Multiagent Systems - Istanbul, Turkey
Duration: 4 May 20158 May 2015
Conference number: 14

Conference

Conference14th International Conference on Autonomous Agents and Multiagent Systems
Abbreviated titleAAMAS 2015
CountryTurkey
CityIstanbul
Period4/05/158/05/15

Fingerprint

Planning
Labels

Cite this

Porteous, J., Lindsay, A., Read, J., Truran, M., & Cavazza, M. (2015). Automated Extension of Narrative Planning Domains with Antonymic Operators. In AAMAS '15: Proceedings of the 2015 International Conference on Autonomous Agents and Multiagent Systems (pp. 1547-1555). Association for Computing Machinery (ACM).
Porteous, Julie ; Lindsay, Alan ; Read, Jonathon ; Truran, Mark ; Cavazza, Marc. / Automated Extension of Narrative Planning Domains with Antonymic Operators. AAMAS '15: Proceedings of the 2015 International Conference on Autonomous Agents and Multiagent Systems. Association for Computing Machinery (ACM), 2015. pp. 1547-1555
@inproceedings{57e2121a74a04b8a8a5f8c63cb248ab8,
title = "Automated Extension of Narrative Planning Domains with Antonymic Operators",
abstract = "AI Planning has been widely used for narrative generation and the control of virtual actors in interactive storytelling. Planning models for such dynamic environments must include alternative actions which enable deviation away from a baseline storyline in order to generate multiple story variants and to be able to respond to changes that might be made to the story world. However, the actual creation of these domain models has been a largely empirical process with a lack of principled approaches to the definition of alternative actions. Our work has addressed this problem and in the paper we present a novel automated method for the generation of interactive narrative domain models from existing non-interactive versions. Central to this is the use of actions that are contrary to those forming the baseline plot within a principled mechanism for their semi-automatic production. It is important that such newly created domain content should still be human-readable and to this end labels for new actions and predicates are generated automatically using antonyms selected from a range of on-line lexical resources. Our approach is fully implemented in a prototype system and its potential demonstrated via both formal experimental evaluation and user evaluation of the generated action labels.",
keywords = "Interactive Storytelling, Narrative Modelling, Planning, Virtual Agents",
author = "Julie Porteous and Alan Lindsay and Jonathon Read and Mark Truran and Marc Cavazza",
year = "2015",
month = "5",
day = "4",
language = "English",
pages = "1547--1555",
booktitle = "AAMAS '15",
publisher = "Association for Computing Machinery (ACM)",
address = "United States",

}

Porteous, J, Lindsay, A, Read, J, Truran, M & Cavazza, M 2015, Automated Extension of Narrative Planning Domains with Antonymic Operators. in AAMAS '15: Proceedings of the 2015 International Conference on Autonomous Agents and Multiagent Systems. Association for Computing Machinery (ACM), pp. 1547-1555, 14th International Conference on Autonomous Agents and Multiagent Systems, Istanbul, Turkey, 4/05/15.

Automated Extension of Narrative Planning Domains with Antonymic Operators. / Porteous, Julie; Lindsay, Alan; Read, Jonathon; Truran, Mark; Cavazza, Marc.

AAMAS '15: Proceedings of the 2015 International Conference on Autonomous Agents and Multiagent Systems. Association for Computing Machinery (ACM), 2015. p. 1547-1555.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Automated Extension of Narrative Planning Domains with Antonymic Operators

AU - Porteous, Julie

AU - Lindsay, Alan

AU - Read, Jonathon

AU - Truran, Mark

AU - Cavazza, Marc

PY - 2015/5/4

Y1 - 2015/5/4

N2 - AI Planning has been widely used for narrative generation and the control of virtual actors in interactive storytelling. Planning models for such dynamic environments must include alternative actions which enable deviation away from a baseline storyline in order to generate multiple story variants and to be able to respond to changes that might be made to the story world. However, the actual creation of these domain models has been a largely empirical process with a lack of principled approaches to the definition of alternative actions. Our work has addressed this problem and in the paper we present a novel automated method for the generation of interactive narrative domain models from existing non-interactive versions. Central to this is the use of actions that are contrary to those forming the baseline plot within a principled mechanism for their semi-automatic production. It is important that such newly created domain content should still be human-readable and to this end labels for new actions and predicates are generated automatically using antonyms selected from a range of on-line lexical resources. Our approach is fully implemented in a prototype system and its potential demonstrated via both formal experimental evaluation and user evaluation of the generated action labels.

AB - AI Planning has been widely used for narrative generation and the control of virtual actors in interactive storytelling. Planning models for such dynamic environments must include alternative actions which enable deviation away from a baseline storyline in order to generate multiple story variants and to be able to respond to changes that might be made to the story world. However, the actual creation of these domain models has been a largely empirical process with a lack of principled approaches to the definition of alternative actions. Our work has addressed this problem and in the paper we present a novel automated method for the generation of interactive narrative domain models from existing non-interactive versions. Central to this is the use of actions that are contrary to those forming the baseline plot within a principled mechanism for their semi-automatic production. It is important that such newly created domain content should still be human-readable and to this end labels for new actions and predicates are generated automatically using antonyms selected from a range of on-line lexical resources. Our approach is fully implemented in a prototype system and its potential demonstrated via both formal experimental evaluation and user evaluation of the generated action labels.

KW - Interactive Storytelling

KW - Narrative Modelling

KW - Planning

KW - Virtual Agents

M3 - Conference contribution

SP - 1547

EP - 1555

BT - AAMAS '15

PB - Association for Computing Machinery (ACM)

ER -

Porteous J, Lindsay A, Read J, Truran M, Cavazza M. Automated Extension of Narrative Planning Domains with Antonymic Operators. In AAMAS '15: Proceedings of the 2015 International Conference on Autonomous Agents and Multiagent Systems. Association for Computing Machinery (ACM). 2015. p. 1547-1555