BibSonomy :: publication ::

tag user group author concept BibTeX key search:all search:mgrani

The blue social bookmark and publication sharing system.

(0)

This publication has not been reviewed yet.

rating distribution

average user rating

The average rating is computed over all reviews. However, some of them may be invisible to you due to the visibility setting chosen by the reviewers.

(0.0 of 5.0 based on 0 reviews)

Applying Vector Space Models to Ontology Link Type Suggestion

by: Albert Weichselbraun, Gerhard Wohlgenannt, Arno Scharl, Michael Granitzer, Thomas Neidhart, and Andreas Juffinger

In: Proc. 4th International Conference on Innovations in Information Technology Innovations '07 (2007) , p. 566--570.

Abstract

The identification and labeling of non-hierarchical relations are among the most challenging tasks in ontology learning. This paper describes an approach for suggesting ontology relationship types to domain experts based on implicitly learned relations from a domain corpus. The learning process extracts verb- vectors from sentences containing domain concepts. It computes centroids for known relationship types and stores them in the knowledge base. Vectors of unknown relationships are compared to the stored centroids using the cosine similarity metric. The system then suggests the relationship type of the most similar centroid. Domain experts evaluate these suggestions to refine the knowledge base and constantly improve the component's accuracy. Using four sample ontologies on "energy sources", this paper demonstrates how link type suggestion aids the ontology design process. It also provides a statistical analysis on the accuracy and average ranking performance of batch learning versus online learning.

Description

myown conferences

BibTeX record

@inproceedings{IPWeichselbraunWSGranitzerNJ2007VSMForOntologyLinkTypeSuggestion,
  abstract = {The identification and labeling of non-hierarchical relations are
	among the most challenging tasks in ontology learning. This paper
	describes an approach for suggesting ontology relationship types
	to domain experts based on implicitly learned relations from a domain
	corpus. The learning process extracts verb- vectors from sentences
	containing domain concepts. It computes centroids for known relationship
	types and stores them in the knowledge base. Vectors of unknown relationships
	are compared to the stored centroids using the cosine similarity
	metric. The system then suggests the relationship type of the most
	similar centroid. Domain experts evaluate these suggestions to refine
	the knowledge base and constantly improve the component's accuracy.
	Using four sample ontologies on "energy sources", this paper demonstrates
	how link type suggestion aids the ontology design process. It also
	provides a statistical analysis on the accuracy and average ranking
	performance of batch learning versus online learning.},
  added-at = {2008-09-24T20:10:25.000+0200},
  author = {Weichselbraun, Albert and Wohlgenannt, Gerhard and Scharl, Arno and Granitzer, Michael and Neidhart, Thomas and Juffinger, Andreas},
  biburl = {http://www.bibsonomy.org/bibtex/22ef5e728b80a65fe70b8e3891197046e/mgrani},
  booktitle = {Proc. 4th International Conference on Innovations in Information
	Technology Innovations '07},
  description = {myown conferences},
  doi = {10.1109/IIT.2007.4430433},
  interhash = {5718efbca5f96a89e4f9466e10b328e8},
  intrahash = {2ef5e728b80a65fe70b8e3891197046e},
  keywords = {(artificial Web, analysis, based batch conference cosine design intelligence), knowledge learning learning, link metric, models myown nonhierarchical online ontologies ontology process, relations, semantic similarity space statistical suggestion, system, systems, type vector},
  owner = {mgrani},
  pages = {566--570},
  timestamp = {2008-09-24T20:10:25.000+0200},
  title = {Applying Vector Space Models to Ontology Link Type Suggestion},
  year = 2007
}

Endnote record

%0 Conference Paper
%1 IPWeichselbraunWSGranitzerNJ2007VSMForOntologyLinkTypeSuggestion
%A Weichselbraun, Albert
%A Wohlgenannt, Gerhard
%A Scharl, Arno
%A Granitzer, Michael
%A Neidhart, Thomas
%A Juffinger, Andreas
%B Proc. 4th International Conference on Innovations in Information
	Technology Innovations '07
%D 2007
%K 
%P 566--570
%T Applying Vector Space Models to Ontology Link Type Suggestion
%R 10.1109/IIT.2007.4430433
%X The identification and labeling of non-hierarchical relations are
	among the most challenging tasks in ontology learning. This paper
	describes an approach for suggesting ontology relationship types
	to domain experts based on implicitly learned relations from a domain
	corpus. The learning process extracts verb- vectors from sentences
	containing domain concepts. It computes centroids for known relationship
	types and stores them in the knowledge base. Vectors of unknown relationships
	are compared to the stored centroids using the cosine similarity
	metric. The system then suggests the relationship type of the most
	similar centroid. Domain experts evaluate these suggestions to refine
	the knowledge base and constantly improve the component's accuracy.
	Using four sample ontologies on "energy sources", this paper demonstrates
	how link type suggestion aids the ontology design process. It also
	provides a statistical analysis on the accuracy and average ranking
	performance of batch learning versus online learning.