A general strategy for knowledge acquisition from semantically heterogeneous data sources

Doina Caragea, Jie Bao, Vasant Honavar

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

1 Citation (Scopus)

Abstract

With the advent of the Semantic Web, there is increased availability of meta data (ontologies) that make explicit the semantic commitments associated with the data sources. Together with tools for specifying mappings between ontologies, this has opened up for the first time, the possibility of acquiring knowledge from such ontology extended, semantically disparate data sources. Hence, there is an urgent need for machine learning algorithms for building predictive models (e.g., classifiers) in a setting where there is no unique global interpretation of data from semantically disparate sources and it is neither feasible nor desirable to collect data from such sources in a centralized data warehouse. We formulate the problem of learning classifiers from a set of related, semantically heterogeneous data sources, under the assumption that ontologies and mappings from a user ontology to the data source ontologies are given. We design a general strategy for learning classifiers from such data sources by reducing the problem of learning to the problem of answering queries from semantically heterogeneous data and we show how to answer such queries.

Original languageEnglish (US)
Title of host publicationSemantic Web for Collaborative Knowledge Acquisition - Papers from the AAAI Fall Symposium, Technical Report
Pages1-8
Number of pages8
VolumeFS-06-06
StatePublished - Dec 1 2006
Event2006 AAAI Fall Symposium - Arlington, VA, United States
Duration: Oct 13 2006Oct 15 2006

Other

Other2006 AAAI Fall Symposium
CountryUnited States
CityArlington, VA
Period10/13/0610/15/06

Fingerprint

Knowledge acquisition
Ontology
Classifiers
Data warehouses
Semantic Web
Metadata
Learning algorithms
Learning systems
Semantics
Availability

All Science Journal Classification (ASJC) codes

  • Engineering(all)

Cite this

Caragea, D., Bao, J., & Honavar, V. (2006). A general strategy for knowledge acquisition from semantically heterogeneous data sources. In Semantic Web for Collaborative Knowledge Acquisition - Papers from the AAAI Fall Symposium, Technical Report (Vol. FS-06-06, pp. 1-8)
Caragea, Doina ; Bao, Jie ; Honavar, Vasant. / A general strategy for knowledge acquisition from semantically heterogeneous data sources. Semantic Web for Collaborative Knowledge Acquisition - Papers from the AAAI Fall Symposium, Technical Report. Vol. FS-06-06 2006. pp. 1-8
@inproceedings{745605e71f264303acaec16dc6375945,
title = "A general strategy for knowledge acquisition from semantically heterogeneous data sources",
abstract = "With the advent of the Semantic Web, there is increased availability of meta data (ontologies) that make explicit the semantic commitments associated with the data sources. Together with tools for specifying mappings between ontologies, this has opened up for the first time, the possibility of acquiring knowledge from such ontology extended, semantically disparate data sources. Hence, there is an urgent need for machine learning algorithms for building predictive models (e.g., classifiers) in a setting where there is no unique global interpretation of data from semantically disparate sources and it is neither feasible nor desirable to collect data from such sources in a centralized data warehouse. We formulate the problem of learning classifiers from a set of related, semantically heterogeneous data sources, under the assumption that ontologies and mappings from a user ontology to the data source ontologies are given. We design a general strategy for learning classifiers from such data sources by reducing the problem of learning to the problem of answering queries from semantically heterogeneous data and we show how to answer such queries.",
author = "Doina Caragea and Jie Bao and Vasant Honavar",
year = "2006",
month = "12",
day = "1",
language = "English (US)",
isbn = "1577353048",
volume = "FS-06-06",
pages = "1--8",
booktitle = "Semantic Web for Collaborative Knowledge Acquisition - Papers from the AAAI Fall Symposium, Technical Report",

}

Caragea, D, Bao, J & Honavar, V 2006, A general strategy for knowledge acquisition from semantically heterogeneous data sources. in Semantic Web for Collaborative Knowledge Acquisition - Papers from the AAAI Fall Symposium, Technical Report. vol. FS-06-06, pp. 1-8, 2006 AAAI Fall Symposium, Arlington, VA, United States, 10/13/06.

A general strategy for knowledge acquisition from semantically heterogeneous data sources. / Caragea, Doina; Bao, Jie; Honavar, Vasant.

Semantic Web for Collaborative Knowledge Acquisition - Papers from the AAAI Fall Symposium, Technical Report. Vol. FS-06-06 2006. p. 1-8.

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

TY - GEN

T1 - A general strategy for knowledge acquisition from semantically heterogeneous data sources

AU - Caragea, Doina

AU - Bao, Jie

AU - Honavar, Vasant

PY - 2006/12/1

Y1 - 2006/12/1

N2 - With the advent of the Semantic Web, there is increased availability of meta data (ontologies) that make explicit the semantic commitments associated with the data sources. Together with tools for specifying mappings between ontologies, this has opened up for the first time, the possibility of acquiring knowledge from such ontology extended, semantically disparate data sources. Hence, there is an urgent need for machine learning algorithms for building predictive models (e.g., classifiers) in a setting where there is no unique global interpretation of data from semantically disparate sources and it is neither feasible nor desirable to collect data from such sources in a centralized data warehouse. We formulate the problem of learning classifiers from a set of related, semantically heterogeneous data sources, under the assumption that ontologies and mappings from a user ontology to the data source ontologies are given. We design a general strategy for learning classifiers from such data sources by reducing the problem of learning to the problem of answering queries from semantically heterogeneous data and we show how to answer such queries.

AB - With the advent of the Semantic Web, there is increased availability of meta data (ontologies) that make explicit the semantic commitments associated with the data sources. Together with tools for specifying mappings between ontologies, this has opened up for the first time, the possibility of acquiring knowledge from such ontology extended, semantically disparate data sources. Hence, there is an urgent need for machine learning algorithms for building predictive models (e.g., classifiers) in a setting where there is no unique global interpretation of data from semantically disparate sources and it is neither feasible nor desirable to collect data from such sources in a centralized data warehouse. We formulate the problem of learning classifiers from a set of related, semantically heterogeneous data sources, under the assumption that ontologies and mappings from a user ontology to the data source ontologies are given. We design a general strategy for learning classifiers from such data sources by reducing the problem of learning to the problem of answering queries from semantically heterogeneous data and we show how to answer such queries.

UR - http://www.scopus.com/inward/record.url?scp=33947230178&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33947230178&partnerID=8YFLogxK

M3 - Conference contribution

SN - 1577353048

SN - 9781577353041

VL - FS-06-06

SP - 1

EP - 8

BT - Semantic Web for Collaborative Knowledge Acquisition - Papers from the AAAI Fall Symposium, Technical Report

ER -

Caragea D, Bao J, Honavar V. A general strategy for knowledge acquisition from semantically heterogeneous data sources. In Semantic Web for Collaborative Knowledge Acquisition - Papers from the AAAI Fall Symposium, Technical Report. Vol. FS-06-06. 2006. p. 1-8