by Michael McHale
Abstract:
This paper presents the results of using Roget's International Thesaurus as the taxonomy in a semantic similarity measurement task. Four similarity metrics were taken from the literature and applied to Roget's The experimental evaluation suggests that the traditional edge counting approach does surprisingly well (a correlation of r=0.88 with a benchmark set of human similarity judgements, with an upper bound of r=0.90 for human subjects performing the same task.)
Reference:
A Comparison of WordNet and Roget's Taxonomy for Measuring Semantic Similarity (Michael McHale), In COLING/ACL Workshop on Usage of WordNet in Natural Language Processing System, 1998.
Bibtex Entry:
@inproceedings{Hale1998,
abstract = {This paper presents the results of using Roget's International Thesaurus as the taxonomy in a semantic similarity measurement task. Four similarity metrics were taken from the literature and applied to Roget's The experimental evaluation suggests that the traditional edge counting approach does surprisingly well (a correlation of r=0.88 with a benchmark set of human similarity judgements, with an upper bound of r=0.90 for human subjects performing the same task.)},
author = {McHale, Michael},
booktitle = {COLING/ACL Workshop on Usage of WordNet in Natural Language Processing System},
keywords = {SML-LIB-BIBLIO,lang:ENG},
mendeley-tags = {SML-LIB-BIBLIO,lang:ENG},
pages = {115----120},
title = {{A Comparison of WordNet and Roget's Taxonomy for Measuring Semantic Similarity}},
url = {http://arxiv.org/abs/cmp-lg/9809003},
year = {1998}
}