Learning of alignment rules between concept hierarchies

Ryutaro Ichise, Hideaki Takeda, Shinichi Honiden

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

With the rapid advances of information technology, we are acquiring much information than ever before. As a result, we need tools for organizing this data. Concept hierarchies such as ontologies and information categorizations are powerful and convenient methods for accomplishing this goal, which have gained wide spread acceptance. Although each concept hierarchy is useful, it is difficult to employ multiple concept hierarchies at the same time because it is hard to align their conceptual structures. This paper proposes a rule learning method that inputs information from a source concept hierarchy and finds suitable location for them in a target hierarchy. The key idea is to find the most similar categories in each hierarchy, where similarity is measured by the K(kappa) statistic that counts instances belonging to both categories. In order to evaluate our method, we conducted experiments using two internet directories: Yahoo! and LYCOS. We map information instances from the source directory into the target directory, and show that our learned rules agree with a human-generated assignment 76% of the time.

Original languageEnglish
Pages (from-to)230-238
Number of pages9
JournalTransactions of the Japanese Society for Artificial Intelligence
Volume17
Issue number3
DOIs
Publication statusPublished - 2002 Dec 1
Externally publishedYes

Fingerprint

Information technology
Ontology
Statistics
Internet
Experiments

Keywords

  • Categorization
  • Concept hierarchy
  • Machine learning
  • Web mining

ASJC Scopus subject areas

  • Artificial Intelligence

Cite this

Learning of alignment rules between concept hierarchies. / Ichise, Ryutaro; Takeda, Hideaki; Honiden, Shinichi.

In: Transactions of the Japanese Society for Artificial Intelligence, Vol. 17, No. 3, 01.12.2002, p. 230-238.

Research output: Contribution to journalArticle

@article{d91285f09c124c838d1f9670495cc04f,
title = "Learning of alignment rules between concept hierarchies",
abstract = "With the rapid advances of information technology, we are acquiring much information than ever before. As a result, we need tools for organizing this data. Concept hierarchies such as ontologies and information categorizations are powerful and convenient methods for accomplishing this goal, which have gained wide spread acceptance. Although each concept hierarchy is useful, it is difficult to employ multiple concept hierarchies at the same time because it is hard to align their conceptual structures. This paper proposes a rule learning method that inputs information from a source concept hierarchy and finds suitable location for them in a target hierarchy. The key idea is to find the most similar categories in each hierarchy, where similarity is measured by the K(kappa) statistic that counts instances belonging to both categories. In order to evaluate our method, we conducted experiments using two internet directories: Yahoo! and LYCOS. We map information instances from the source directory into the target directory, and show that our learned rules agree with a human-generated assignment 76{\%} of the time.",
keywords = "Categorization, Concept hierarchy, Machine learning, Web mining",
author = "Ryutaro Ichise and Hideaki Takeda and Shinichi Honiden",
year = "2002",
month = "12",
day = "1",
doi = "10.1527/tjsai.17.230",
language = "English",
volume = "17",
pages = "230--238",
journal = "Transactions of the Japanese Society for Artificial Intelligence",
issn = "1346-0714",
publisher = "Japanese Society for Artificial Intelligence",
number = "3",

}

TY - JOUR

T1 - Learning of alignment rules between concept hierarchies

AU - Ichise, Ryutaro

AU - Takeda, Hideaki

AU - Honiden, Shinichi

PY - 2002/12/1

Y1 - 2002/12/1

N2 - With the rapid advances of information technology, we are acquiring much information than ever before. As a result, we need tools for organizing this data. Concept hierarchies such as ontologies and information categorizations are powerful and convenient methods for accomplishing this goal, which have gained wide spread acceptance. Although each concept hierarchy is useful, it is difficult to employ multiple concept hierarchies at the same time because it is hard to align their conceptual structures. This paper proposes a rule learning method that inputs information from a source concept hierarchy and finds suitable location for them in a target hierarchy. The key idea is to find the most similar categories in each hierarchy, where similarity is measured by the K(kappa) statistic that counts instances belonging to both categories. In order to evaluate our method, we conducted experiments using two internet directories: Yahoo! and LYCOS. We map information instances from the source directory into the target directory, and show that our learned rules agree with a human-generated assignment 76% of the time.

AB - With the rapid advances of information technology, we are acquiring much information than ever before. As a result, we need tools for organizing this data. Concept hierarchies such as ontologies and information categorizations are powerful and convenient methods for accomplishing this goal, which have gained wide spread acceptance. Although each concept hierarchy is useful, it is difficult to employ multiple concept hierarchies at the same time because it is hard to align their conceptual structures. This paper proposes a rule learning method that inputs information from a source concept hierarchy and finds suitable location for them in a target hierarchy. The key idea is to find the most similar categories in each hierarchy, where similarity is measured by the K(kappa) statistic that counts instances belonging to both categories. In order to evaluate our method, we conducted experiments using two internet directories: Yahoo! and LYCOS. We map information instances from the source directory into the target directory, and show that our learned rules agree with a human-generated assignment 76% of the time.

KW - Categorization

KW - Concept hierarchy

KW - Machine learning

KW - Web mining

UR - http://www.scopus.com/inward/record.url?scp=18544373046&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=18544373046&partnerID=8YFLogxK

U2 - 10.1527/tjsai.17.230

DO - 10.1527/tjsai.17.230

M3 - Article

AN - SCOPUS:18544373046

VL - 17

SP - 230

EP - 238

JO - Transactions of the Japanese Society for Artificial Intelligence

JF - Transactions of the Japanese Society for Artificial Intelligence

SN - 1346-0714

IS - 3

ER -