We propose a novel algorithm for inducing semantic taxonomies. Previous algorithms for taxonomy induction have typically focused on independent classifiers for discovering new single relationships based on hand-constructed or automatically discovered textual patterns. By contrast, our algorithm flexibly incorporates evidence from multiple classifiers over heterogenous relationships to optimize the entire structure of the taxonomy, using knowledge of a word’s coordinate terms to help in determining its hypernyms, and vice versa. We apply our algorithm on the problem of sense-disambiguated noun hyponym acquisition, where we combine the predictions of hypernym and coordinate term classifiers with the knowledge in a preexisting semantic taxonomy (WordNet 2.1). We add 10; 000 novel synsets to WordNet 2.1 at 84% precision, a relative error reduction of 70% over a non-joint algorithm using the same component classifiers. Finally, we show that a taxonomy built using our algorithm shows a 23% relative F-score improvement over WordNet 2.1 on an independent testset of hypernym pairs.
%0 Conference Paper
%1 snow2006semantic
%A Snow, Rion
%A Jurafsky, Daniel
%A Ng, Andrew Y.
%B ACL
%D 2006
%I The Association for Computer Linguistics
%K ol ol_web2.0 ontology_learning taxonomies toread toread_dbe methods_concepthierarchy
%T Semantic Taxonomy Induction from Heterogenous Evidence.
%U http://dblp.uni-trier.de/db/conf/acl/acl2006.html#SnowJN06
%X We propose a novel algorithm for inducing semantic taxonomies. Previous algorithms for taxonomy induction have typically focused on independent classifiers for discovering new single relationships based on hand-constructed or automatically discovered textual patterns. By contrast, our algorithm flexibly incorporates evidence from multiple classifiers over heterogenous relationships to optimize the entire structure of the taxonomy, using knowledge of a word’s coordinate terms to help in determining its hypernyms, and vice versa. We apply our algorithm on the problem of sense-disambiguated noun hyponym acquisition, where we combine the predictions of hypernym and coordinate term classifiers with the knowledge in a preexisting semantic taxonomy (WordNet 2.1). We add 10; 000 novel synsets to WordNet 2.1 at 84% precision, a relative error reduction of 70% over a non-joint algorithm using the same component classifiers. Finally, we show that a taxonomy built using our algorithm shows a 23% relative F-score improvement over WordNet 2.1 on an independent testset of hypernym pairs.
@inproceedings{snow2006semantic,
abstract = {We propose a novel algorithm for inducing semantic taxonomies. Previous algorithms for taxonomy induction have typically focused on independent classifiers for discovering new single relationships based on hand-constructed or automatically discovered textual patterns. By contrast, our algorithm flexibly incorporates evidence from multiple classifiers over heterogenous relationships to optimize the entire structure of the taxonomy, using knowledge of a word’s coordinate terms to help in determining its hypernyms, and vice versa. We apply our algorithm on the problem of sense-disambiguated noun hyponym acquisition, where we combine the predictions of hypernym and coordinate term classifiers with the knowledge in a preexisting semantic taxonomy (WordNet 2.1). We add 10; 000 novel synsets to WordNet 2.1 at 84% precision, a relative error reduction of 70% over a non-joint algorithm using the same component classifiers. Finally, we show that a taxonomy built using our algorithm shows a 23% relative F-score improvement over WordNet 2.1 on an independent testset of hypernym pairs.},
added-at = {2011-02-17T17:43:08.000+0100},
author = {Snow, Rion and Jurafsky, Daniel and Ng, Andrew Y.},
biburl = {https://www.bibsonomy.org/bibtex/28f39e7ac43a97719c5a746da02dbd964/dbenz},
booktitle = {ACL},
crossref = {conf/acl/2006},
description = {dblp},
ee = {http://acl.ldc.upenn.edu/P/P06/P06-1101.pdf},
file = {snow2006semantic.pdf:snow2006semantic.pdf:PDF},
groups = {public},
interhash = {c0f5a3a22faa8dc4b61c9a717a6c9037},
intrahash = {8f39e7ac43a97719c5a746da02dbd964},
keywords = {ol ol_web2.0 ontology_learning taxonomies toread toread_dbe methods_concepthierarchy},
publisher = {The Association for Computer Linguistics},
timestamp = {2013-07-31T15:39:42.000+0200},
title = {Semantic Taxonomy Induction from Heterogenous Evidence.},
url = {http://dblp.uni-trier.de/db/conf/acl/acl2006.html#SnowJN06},
username = {dbenz},
year = 2006
}