Semantic Similarity Based on Corpus Statistics and Lexical Taxonomy
J. Jiang, and D. Conrath. (1997)cite arxiv:cmp-lg/9709008Comment: 15 pages, Postscript only.
Abstract
This paper presents a new approach for measuring semantic similarity/distance
between words and concepts. It combines a lexical taxonomy structure with
corpus statistical information so that the semantic distance between nodes in
the semantic space constructed by the taxonomy can be better quantified with
the computational evidence derived from a distributional analysis of corpus
data. Specifically, the proposed measure is a combined approach that inherits
the edge-based approach of the edge counting scheme, which is then enhanced by
the node-based approach of the information content calculation. When tested on
a common data set of word pair similarity ratings, the proposed approach
outperforms other computational models. It gives the highest correlation value
(r = 0.828) with a benchmark based on human similarity judgements, whereas an
upper bound (r = 0.885) is observed when human subjects replicate the same
task.
%0 Conference Paper
%1 jiang1997semantic
%A Jiang, Jay J.
%A Conrath, David W.
%D 1997
%K conrath diss16 jiang semantic similarity wordnet
%T Semantic Similarity Based on Corpus Statistics and Lexical Taxonomy
%U http://arxiv.org/abs/cmp-lg/9709008
%X This paper presents a new approach for measuring semantic similarity/distance
between words and concepts. It combines a lexical taxonomy structure with
corpus statistical information so that the semantic distance between nodes in
the semantic space constructed by the taxonomy can be better quantified with
the computational evidence derived from a distributional analysis of corpus
data. Specifically, the proposed measure is a combined approach that inherits
the edge-based approach of the edge counting scheme, which is then enhanced by
the node-based approach of the information content calculation. When tested on
a common data set of word pair similarity ratings, the proposed approach
outperforms other computational models. It gives the highest correlation value
(r = 0.828) with a benchmark based on human similarity judgements, whereas an
upper bound (r = 0.885) is observed when human subjects replicate the same
task.
@inproceedings{jiang1997semantic,
abstract = {This paper presents a new approach for measuring semantic similarity/distance
between words and concepts. It combines a lexical taxonomy structure with
corpus statistical information so that the semantic distance between nodes in
the semantic space constructed by the taxonomy can be better quantified with
the computational evidence derived from a distributional analysis of corpus
data. Specifically, the proposed measure is a combined approach that inherits
the edge-based approach of the edge counting scheme, which is then enhanced by
the node-based approach of the information content calculation. When tested on
a common data set of word pair similarity ratings, the proposed approach
outperforms other computational models. It gives the highest correlation value
(r = 0.828) with a benchmark based on human similarity judgements, whereas an
upper bound (r = 0.885) is observed when human subjects replicate the same
task.},
added-at = {2015-12-07T13:23:21.000+0100},
author = {Jiang, Jay J. and Conrath, David W.},
biburl = {https://www.bibsonomy.org/bibtex/297dc1d5b4fb8f8cb113ba2eebac59e75/thoni},
interhash = {175ec03ee8c47d4b2d0a083609a78e05},
intrahash = {97dc1d5b4fb8f8cb113ba2eebac59e75},
keywords = {conrath diss16 jiang semantic similarity wordnet},
note = {cite arxiv:cmp-lg/9709008Comment: 15 pages, Postscript only},
timestamp = {2016-09-06T08:23:07.000+0200},
title = {Semantic Similarity Based on Corpus Statistics and Lexical Taxonomy},
url = {http://arxiv.org/abs/cmp-lg/9709008},
year = 1997
}