Framer: Planning Models from Natural Language Action Descriptions

Hdl Handle:
http://hdl.handle.net/10149/620942
Title:
Framer: Planning Models from Natural Language Action Descriptions
Authors:
Lindsay, A. (Alan); Read, J. (Jonathon); Ferreira, J. F. (João); Hayton, T. (Thomas); Porteous, J. (Julie); Gregory, P. J. (Peter)
Affiliation:
Teesside University. Digital Futures Institute
Conference:
The 27th International Conference on Automated Planning and Scheduling, Pittsburgh, USA - June 18 - 23, 2017.
Issue Date:
18-Jun-2017
URI:
http://hdl.handle.net/10149/620942
Additional Links:
http://icaps17.icaps-conference.org/
Abstract:
In this paper, we describe an approach for learning planning domain models directly from natural language (NL) descriptions of activity sequences. The modelling problem has been identified as a bottleneck for the widespread exploitation of various technologies in Artificial Intelligence, including automated planners. There have been great advances in modelling assisting and model generation tools, including a wide range of domain model acquisition tools. However, for modelling tools, there is the underlying assumption that the user can formulate the problem using some formal language. And even in the case of the domain model acquisition tools, there is still a requirement to specify input plans in an easily machine readable format. Providing this type of input is impractical for many potential users. This motivates us to generate planning domain models directly from NL descriptions, as this would provide an important step in extending the widespread adoption of planning techniques. We start from NL descriptions of actions and use NL analysis to construct structured representations, from which we construct formal representations of the action sequences. The generated action sequences provide the necessary structured input for inducing a PDDL domain, using domain model acquisition technology. In order to capture a concise planning model, we use an estimate of functional similarity, so sentences that describe similar behaviours are represented by the same planning operator. We validate our approach with a user study, where participants are tasked with describing the activities occurring in several videos. Then our system is used to learn planning domain models using the participants’ NL input.We demonstrate that our approach is effective at learning models on these tasks.
Type:
Meetings and Proceedings
Language:
en

Full metadata record

DC FieldValue Language
dc.contributor.authorLindsay, A. (Alan)en
dc.contributor.authorRead, J. (Jonathon)en
dc.contributor.authorFerreira, J. F. (João)en
dc.contributor.authorHayton, T. (Thomas)en
dc.contributor.authorPorteous, J. (Julie)en
dc.contributor.authorGregory, P. J. (Peter)en
dc.date.accessioned2017-03-29T14:29:20Z-
dc.date.available2017-03-29T14:29:20Z-
dc.date.issued2017-06-18-
dc.identifier.urihttp://hdl.handle.net/10149/620942-
dc.description.abstractIn this paper, we describe an approach for learning planning domain models directly from natural language (NL) descriptions of activity sequences. The modelling problem has been identified as a bottleneck for the widespread exploitation of various technologies in Artificial Intelligence, including automated planners. There have been great advances in modelling assisting and model generation tools, including a wide range of domain model acquisition tools. However, for modelling tools, there is the underlying assumption that the user can formulate the problem using some formal language. And even in the case of the domain model acquisition tools, there is still a requirement to specify input plans in an easily machine readable format. Providing this type of input is impractical for many potential users. This motivates us to generate planning domain models directly from NL descriptions, as this would provide an important step in extending the widespread adoption of planning techniques. We start from NL descriptions of actions and use NL analysis to construct structured representations, from which we construct formal representations of the action sequences. The generated action sequences provide the necessary structured input for inducing a PDDL domain, using domain model acquisition technology. In order to capture a concise planning model, we use an estimate of functional similarity, so sentences that describe similar behaviours are represented by the same planning operator. We validate our approach with a user study, where participants are tasked with describing the activities occurring in several videos. Then our system is used to learn planning domain models using the participants’ NL input.We demonstrate that our approach is effective at learning models on these tasks.en
dc.language.isoenen
dc.relation.urlhttp://icaps17.icaps-conference.org/en
dc.titleFramer: Planning Models from Natural Language Action Descriptionsen
dc.typeMeetings and Proceedingsen
dc.contributor.departmentTeesside University. Digital Futures Instituteen
dc.identifier.conferenceThe 27th International Conference on Automated Planning and Scheduling, Pittsburgh, USA - June 18 - 23, 2017.en
dc.eprint.versionPost-printen
dc.date.accepted2017-01-26-
All Items in TeesRep are protected by copyright, with all rights reserved, unless otherwise indicated.