Ontology evolution through agent collaboration
Ontology evolution through agent collaboration
We present a technique that enables a software agent to augment its ontology with domain related concepts by collaborating with other agents. The collaborating agents have their own individual ontologies, they can share concepts and relationships that relate to a requested specific concept (which is known as a fragment). Thus, specifically, our technique selects the fragments that will be shared. This approach enables agents to answer queries with more range and detail, and it also enables an agent to infer new exploitable knowledge. Without this capability, an agent may be limited by its domain model, and cannot reflect changes in the environment. Through empirical evaluation, we show that our technique reduces the cost of acquiring concepts that are regularly used (compared with learning nothing) and reduces the complexity of the agent's ontology by augmenting it with selected concepts and relationships which are related to its domain (compared with learning everything).
Packer, Heather S.
f379270a-d030-4861-a2bf-6c6d7b075b7e
Gibbins, Nicholas
98efd447-4aa7-411c-86d1-955a612eceac
Jennings, Nicholas R
ab3d94cc-247c-4545-9d1e-65873d6cdb30
April 2009
Packer, Heather S.
f379270a-d030-4861-a2bf-6c6d7b075b7e
Gibbins, Nicholas
98efd447-4aa7-411c-86d1-955a612eceac
Jennings, Nicholas R
ab3d94cc-247c-4545-9d1e-65873d6cdb30
Packer, Heather S., Gibbins, Nicholas and Jennings, Nicholas R
(2009)
Ontology evolution through agent collaboration.
Workshop on Matching and Meaning 2009: Automated Development, Evolution and Interpretation of Ontologies, Edinburgh, United Kingdom.
09 Apr 2009.
Record type:
Conference or Workshop Item
(Paper)
Abstract
We present a technique that enables a software agent to augment its ontology with domain related concepts by collaborating with other agents. The collaborating agents have their own individual ontologies, they can share concepts and relationships that relate to a requested specific concept (which is known as a fragment). Thus, specifically, our technique selects the fragments that will be shared. This approach enables agents to answer queries with more range and detail, and it also enables an agent to infer new exploitable knowledge. Without this capability, an agent may be limited by its domain model, and cannot reflect changes in the environment. Through empirical evaluation, we show that our technique reduces the cost of acquiring concepts that are regularly used (compared with learning nothing) and reduces the complexity of the agent's ontology by augmenting it with selected concepts and relationships which are related to its domain (compared with learning everything).
Text
AISB2009.pdf
- Accepted Manuscript
More information
Published date: April 2009
Additional Information:
Artificial Intelligence and Simulation of Behaviour 2009 Convention
Venue - Dates:
Workshop on Matching and Meaning 2009: Automated Development, Evolution and Interpretation of Ontologies, Edinburgh, United Kingdom, 2009-04-09 - 2009-04-09
Identifiers
Local EPrints ID: 65690
URI: http://eprints.soton.ac.uk/id/eprint/65690
PURE UUID: 2879f1cb-9cab-4dba-bc95-ee9f28d96598
Catalogue record
Date deposited: 10 Mar 2009
Last modified: 14 Mar 2024 02:42
Export record
Contributors
Author:
Heather S. Packer
Author:
Nicholas Gibbins
Author:
Nicholas R Jennings
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics