Learning link-based classifiers from ontology-extended textual data

Cornelia Caragea, Doina Caragea, Vasant Honavar

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

2 Citations (Scopus)

Abstract

Real-world data mining applications call for effective strategies for learning predictive models from richly structured relational data. In this paper, we address the problem of learning classifiers from structured relational data that are annotated with relevant meta data. Specifically, we show how to learn classifiers at different levels of abstraction in a relational setting, where the structured relational data are organized in an abstraction hierarchy that describes the semantics of the content of the data. We show how to cope with some of the challenges presented by partial specification in the case of structured data, that unavoidably results from choosing a particular level of abstraction. Our solution to partial specification is based on a statistical method, called shrinkage. We present results of experiments in the case of learning link-based Naïve Bayes classifiers on a text classification task that (i) demonstrate that the choice of the level of abstraction can impact the performance of the resulting link-based classifiers and (ii) examine the effect of partially specified data.

Original languageEnglish (US)
Title of host publicationICTAI 2009 - 21st IEEE International Conference on Tools with Artificial Intelligence
Pages354-361
Number of pages8
DOIs
StatePublished - Dec 1 2009
Event21st IEEE International Conference on Tools with Artificial Intelligence, ICTAI 2009 - Newark, NJ, United States
Duration: Nov 2 2009Nov 5 2009

Publication series

NameProceedings - International Conference on Tools with Artificial Intelligence, ICTAI
ISSN (Print)1082-3409

Other

Other21st IEEE International Conference on Tools with Artificial Intelligence, ICTAI 2009
CountryUnited States
CityNewark, NJ
Period11/2/0911/5/09

Fingerprint

Ontology
Classifiers
Specifications
Metadata
Data mining
Statistical methods
Semantics
Experiments

All Science Journal Classification (ASJC) codes

  • Software
  • Artificial Intelligence
  • Computer Science Applications

Cite this

Caragea, C., Caragea, D., & Honavar, V. (2009). Learning link-based classifiers from ontology-extended textual data. In ICTAI 2009 - 21st IEEE International Conference on Tools with Artificial Intelligence (pp. 354-361). [5364346] (Proceedings - International Conference on Tools with Artificial Intelligence, ICTAI). https://doi.org/10.1109/ICTAI.2009.111
Caragea, Cornelia ; Caragea, Doina ; Honavar, Vasant. / Learning link-based classifiers from ontology-extended textual data. ICTAI 2009 - 21st IEEE International Conference on Tools with Artificial Intelligence. 2009. pp. 354-361 (Proceedings - International Conference on Tools with Artificial Intelligence, ICTAI).
@inproceedings{7e0bb1958516484c8ac744680a6bfa80,
title = "Learning link-based classifiers from ontology-extended textual data",
abstract = "Real-world data mining applications call for effective strategies for learning predictive models from richly structured relational data. In this paper, we address the problem of learning classifiers from structured relational data that are annotated with relevant meta data. Specifically, we show how to learn classifiers at different levels of abstraction in a relational setting, where the structured relational data are organized in an abstraction hierarchy that describes the semantics of the content of the data. We show how to cope with some of the challenges presented by partial specification in the case of structured data, that unavoidably results from choosing a particular level of abstraction. Our solution to partial specification is based on a statistical method, called shrinkage. We present results of experiments in the case of learning link-based Na{\"i}ve Bayes classifiers on a text classification task that (i) demonstrate that the choice of the level of abstraction can impact the performance of the resulting link-based classifiers and (ii) examine the effect of partially specified data.",
author = "Cornelia Caragea and Doina Caragea and Vasant Honavar",
year = "2009",
month = "12",
day = "1",
doi = "10.1109/ICTAI.2009.111",
language = "English (US)",
isbn = "9781424456192",
series = "Proceedings - International Conference on Tools with Artificial Intelligence, ICTAI",
pages = "354--361",
booktitle = "ICTAI 2009 - 21st IEEE International Conference on Tools with Artificial Intelligence",

}

Caragea, C, Caragea, D & Honavar, V 2009, Learning link-based classifiers from ontology-extended textual data. in ICTAI 2009 - 21st IEEE International Conference on Tools with Artificial Intelligence., 5364346, Proceedings - International Conference on Tools with Artificial Intelligence, ICTAI, pp. 354-361, 21st IEEE International Conference on Tools with Artificial Intelligence, ICTAI 2009, Newark, NJ, United States, 11/2/09. https://doi.org/10.1109/ICTAI.2009.111

Learning link-based classifiers from ontology-extended textual data. / Caragea, Cornelia; Caragea, Doina; Honavar, Vasant.

ICTAI 2009 - 21st IEEE International Conference on Tools with Artificial Intelligence. 2009. p. 354-361 5364346 (Proceedings - International Conference on Tools with Artificial Intelligence, ICTAI).

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

TY - GEN

T1 - Learning link-based classifiers from ontology-extended textual data

AU - Caragea, Cornelia

AU - Caragea, Doina

AU - Honavar, Vasant

PY - 2009/12/1

Y1 - 2009/12/1

N2 - Real-world data mining applications call for effective strategies for learning predictive models from richly structured relational data. In this paper, we address the problem of learning classifiers from structured relational data that are annotated with relevant meta data. Specifically, we show how to learn classifiers at different levels of abstraction in a relational setting, where the structured relational data are organized in an abstraction hierarchy that describes the semantics of the content of the data. We show how to cope with some of the challenges presented by partial specification in the case of structured data, that unavoidably results from choosing a particular level of abstraction. Our solution to partial specification is based on a statistical method, called shrinkage. We present results of experiments in the case of learning link-based Naïve Bayes classifiers on a text classification task that (i) demonstrate that the choice of the level of abstraction can impact the performance of the resulting link-based classifiers and (ii) examine the effect of partially specified data.

AB - Real-world data mining applications call for effective strategies for learning predictive models from richly structured relational data. In this paper, we address the problem of learning classifiers from structured relational data that are annotated with relevant meta data. Specifically, we show how to learn classifiers at different levels of abstraction in a relational setting, where the structured relational data are organized in an abstraction hierarchy that describes the semantics of the content of the data. We show how to cope with some of the challenges presented by partial specification in the case of structured data, that unavoidably results from choosing a particular level of abstraction. Our solution to partial specification is based on a statistical method, called shrinkage. We present results of experiments in the case of learning link-based Naïve Bayes classifiers on a text classification task that (i) demonstrate that the choice of the level of abstraction can impact the performance of the resulting link-based classifiers and (ii) examine the effect of partially specified data.

UR - http://www.scopus.com/inward/record.url?scp=77949501515&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77949501515&partnerID=8YFLogxK

U2 - 10.1109/ICTAI.2009.111

DO - 10.1109/ICTAI.2009.111

M3 - Conference contribution

AN - SCOPUS:77949501515

SN - 9781424456192

T3 - Proceedings - International Conference on Tools with Artificial Intelligence, ICTAI

SP - 354

EP - 361

BT - ICTAI 2009 - 21st IEEE International Conference on Tools with Artificial Intelligence

ER -

Caragea C, Caragea D, Honavar V. Learning link-based classifiers from ontology-extended textual data. In ICTAI 2009 - 21st IEEE International Conference on Tools with Artificial Intelligence. 2009. p. 354-361. 5364346. (Proceedings - International Conference on Tools with Artificial Intelligence, ICTAI). https://doi.org/10.1109/ICTAI.2009.111