Comparing Wikipedia and German Wordnet by Evaluating Semantic Relatedness on Multiple Datasets
T. Zesch, I. Gurevych, and M. Mühlhäuser. Proceedings of Human Language Technologies: The Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL-HLT), (2007)
Abstract
We evaluate semantic relatedness mea- sures on different German datasets show- ing that their performance depends on: (i) the definition of relatedness that was underlying the construction of the evaluation dataset, and (ii) the knowledge source used for computing semantic relatedness. We analyze how the underlying knowledge source influences the performance of a measure. Finally, we investigate the combination of wordnets and Wikipedia to improve the performance of semantic re- latedness measures.
Proceedings of Human Language Technologies: The Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL-HLT)
%0 Conference Paper
%1 citeulike:2348609
%A Zesch, Torsten
%A Gurevych, Iryna
%A Mühlhäuser, Max
%B Proceedings of Human Language Technologies: The Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL-HLT)
%D 2007
%K READ WW-MUST relatedness wikipedia wordnet
%T Comparing Wikipedia and German Wordnet by Evaluating Semantic Relatedness on Multiple Datasets
%U http://elara.tk.informatik.tu-darmstadt.de/publications/2007/hlt-short.pdf
%X We evaluate semantic relatedness mea- sures on different German datasets show- ing that their performance depends on: (i) the definition of relatedness that was underlying the construction of the evaluation dataset, and (ii) the knowledge source used for computing semantic relatedness. We analyze how the underlying knowledge source influences the performance of a measure. Finally, we investigate the combination of wordnets and Wikipedia to improve the performance of semantic re- latedness measures.
@inproceedings{citeulike:2348609,
abstract = {We evaluate semantic relatedness mea- sures on different German datasets show- ing that their performance depends on: (i) the definition of relatedness that was underlying the construction of the evaluation dataset, and (ii) the knowledge source used for computing semantic relatedness. We analyze how the underlying knowledge source influences the performance of a measure. Finally, we investigate the combination of wordnets and Wikipedia to improve the performance of semantic re- latedness measures.},
added-at = {2008-02-26T23:54:34.000+0100},
author = {Zesch, Torsten and Gurevych, Iryna and Mühlhäuser, Max},
biburl = {https://www.bibsonomy.org/bibtex/20d94192305149e10721d3a8f9ca8bb0a/brightbyte},
booktitle = {Proceedings of Human Language Technologies: The Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL-HLT)},
citeulike-article-id = {2348609},
description = {stuff from citeyoulike},
interhash = {79185082dcbab3df88b21b69f1ad797a},
intrahash = {0d94192305149e10721d3a8f9ca8bb0a},
keywords = {READ WW-MUST relatedness wikipedia wordnet},
priority = {0},
school = {Darmstadt University of Technology},
timestamp = {2009-01-23T09:58:50.000+0100},
title = {Comparing Wikipedia and German Wordnet by Evaluating Semantic Relatedness on Multiple Datasets},
url = {http://elara.tk.informatik.tu-darmstadt.de/publications/2007/hlt-short.pdf},
year = 2007
}