H. Hjelm, and P. Buitelaar. ECAI, volume 178 of Frontiers in Artificial Intelligence and Applications, page 288-292. IOS Press, (2008)
Abstract
We present a system for taxonomy extraction, aimed at providing a taxonomic backbone in an ontology learning environment. We follow previous research in using hierarchical clustering based on distributional similarity of the terms in texts. We show that basing the clustering on a comparable corpus in four languages gives a considerable improvement in accuracy compared to using only the monolingual English texts. We also show that hierarchical k-means clustering increases the similarity to the original taxonomy, when compared with a bottom-up agglomerative clustering approach.
%0 Conference Paper
%1 hjelm2008multilingual
%A Hjelm, Hans
%A Buitelaar, Paul
%B ECAI
%D 2008
%E Ghallab, Malik
%E Spyropoulos, Constantine D.
%E Fakotakis, Nikos
%E Avouris, Nikolaos M.
%I IOS Press
%K ontology_learning toread ol_web2.0 toread_dbe methods_concepthierarchy
%P 288-292
%T Multilingual Evidence Improves Clustering-based Taxonomy Extraction.
%U http://www.ling.su.se/staff/hans/artiklar/ecai2008-hjelm-buitelaar.pdf
%V 178
%X We present a system for taxonomy extraction, aimed at providing a taxonomic backbone in an ontology learning environment. We follow previous research in using hierarchical clustering based on distributional similarity of the terms in texts. We show that basing the clustering on a comparable corpus in four languages gives a considerable improvement in accuracy compared to using only the monolingual English texts. We also show that hierarchical k-means clustering increases the similarity to the original taxonomy, when compared with a bottom-up agglomerative clustering approach.
%@ 978-1-58603-891-5
@inproceedings{hjelm2008multilingual,
abstract = {We present a system for taxonomy extraction, aimed at providing a taxonomic backbone in an ontology learning environment. We follow previous research in using hierarchical clustering based on distributional similarity of the terms in texts. We show that basing the clustering on a comparable corpus in four languages gives a considerable improvement in accuracy compared to using only the monolingual English texts. We also show that hierarchical k-means clustering increases the similarity to the original taxonomy, when compared with a bottom-up agglomerative clustering approach.},
added-at = {2011-02-17T17:42:27.000+0100},
author = {Hjelm, Hans and Buitelaar, Paul},
biburl = {https://www.bibsonomy.org/bibtex/2813903a333a40ecf9a59ded552acb323/dbenz},
booktitle = {ECAI},
crossref = {conf/ecai/2008},
description = {dblp},
editor = {Ghallab, Malik and Spyropoulos, Constantine D. and Fakotakis, Nikos and Avouris, Nikolaos M.},
ee = {http://dx.doi.org/10.3233/978-1-58603-891-5-288},
file = {hjelm2008multilingual.pdf:hjelm2008multilingual.pdf:PDF},
groups = {public},
interhash = {21a658154fb1a02e773b7a678b15f9f4},
intrahash = {813903a333a40ecf9a59ded552acb323},
isbn = {978-1-58603-891-5},
keywords = {ontology_learning toread ol_web2.0 toread_dbe methods_concepthierarchy},
pages = {288-292},
publisher = {IOS Press},
series = {Frontiers in Artificial Intelligence and Applications},
timestamp = {2013-07-31T15:39:42.000+0200},
title = {Multilingual Evidence Improves Clustering-based Taxonomy Extraction.},
url = {http://www.ling.su.se/staff/hans/artiklar/ecai2008-hjelm-buitelaar.pdf},
username = {dbenz},
volume = 178,
year = 2008
}