The emergence of vast quantities of on-line information has raised the importance of methods for automatic cataloguing of information in a variety of domains, including electronic commerce and bioinformatics. Ontologies can play a critical role in such cataloguing. In this paper, we describe a system that automatically induces an ontology from any large on-line text collection in a specific domain. The ontology that is induced consists of domain concepts, related by kind-of and part-of links. To achieve domain-independence, we use a combination of relatively shallow methods along with any available repositories of applicable background knowledge. We describe our evaluation experiences using these methods, and provide examples of induced structures.
%0 Conference Paper
%1 mani2004automatcally
%A Mani, Inderjeet
%A Samuel, Ken
%A Concepcion, Kris
%A Vogel, David
%B Proceedings of the 3rd International Workshop on Computational Terminology
%C Geneva
%D 2004
%K diploma_thesis eventually_useful
%T Automatcally Inducing Ontologies from Corpora
%U http://-new.biomath.jussieu.fr/~pz/computerm2004.html
%X The emergence of vast quantities of on-line information has raised the importance of methods for automatic cataloguing of information in a variety of domains, including electronic commerce and bioinformatics. Ontologies can play a critical role in such cataloguing. In this paper, we describe a system that automatically induces an ontology from any large on-line text collection in a specific domain. The ontology that is induced consists of domain concepts, related by kind-of and part-of links. To achieve domain-independence, we use a combination of relatively shallow methods along with any available repositories of applicable background knowledge. We describe our evaluation experiences using these methods, and provide examples of induced structures.
@inproceedings{mani2004automatcally,
abstract = {The emergence of vast quantities of on-line information has raised the importance of methods for automatic cataloguing of information in a variety of domains, including electronic commerce and bioinformatics. Ontologies can play a critical role in such cataloguing. In this paper, we describe a system that automatically induces an ontology from any large on-line text collection in a specific domain. The ontology that is induced consists of domain concepts, related by kind-of and part-of links. To achieve domain-independence, we use a combination of relatively shallow methods along with any available repositories of applicable background knowledge. We describe our evaluation experiences using these methods, and provide examples of induced structures.},
added-at = {2011-01-28T11:34:25.000+0100},
address = {Geneva},
author = {Mani, Inderjeet and Samuel, Ken and Concepcion, Kris and Vogel, David},
biburl = {https://www.bibsonomy.org/bibtex/2dce5c6301943fe6c9648cf671ceb167e/dbenz},
booktitle = {Proceedings of the 3rd International Workshop on Computational Terminology},
dateadded = {2006-07-18},
interhash = {9ec83ddb1f251792d05345daa8357bf8},
intrahash = {dce5c6301943fe6c9648cf671ceb167e},
keywords = {diploma_thesis eventually_useful},
lastdatemodified = {2006-07-18},
lastname = {Mani},
month = {August},
own = {notown},
pdf = {mani04-automatically.pdf},
read = {notread},
timestamp = {2013-07-31T15:39:42.000+0200},
title = {Automatcally Inducing Ontologies from Corpora},
url = {http://-new.biomath.jussieu.fr/~pz/computerm2004.html},
year = 2004
}