Using the Structure of a Conceptual Network in Computing Semantic Relatedness
I. Gurevych. Proceedings of the Second International Joint Conference on Natural Language Processing, page 767--778. Berlin, Heidelberg, Springer-Verlag, (2005)
DOI: 10.1007/11562214_67
Abstract
We present a new method for computing semantic relatedness of concepts. The method relies solely on the structure of a conceptual network and eliminates the need for performing additional corpus analysis. The network structure is employed to generate artificial conceptual glosses. They replace textual definitions proper written by humans and are processed by a dictionary based metric of semantic relatedness 1. We implemented the metric on the basis of GermaNet, the German counterpart of WordNet, and evaluated the results on a German dataset of 57 word pairs rated by human subjects for their semantic relatedness. Our approach can be easily applied to compute semantic relatedness based on alternative conceptual networks, e.g. in the domain of life sciences.
Description
Using the structure of a conceptual network in computing semantic relatedness
%0 Conference Paper
%1 gurevych2005using
%A Gurevych, Iryna
%B Proceedings of the Second International Joint Conference on Natural Language Processing
%C Berlin, Heidelberg
%D 2005
%I Springer-Verlag
%K conceptual network relatedness semantic wordnet
%P 767--778
%R 10.1007/11562214_67
%T Using the Structure of a Conceptual Network in Computing Semantic Relatedness
%U http://dx.doi.org/10.1007/11562214_67
%X We present a new method for computing semantic relatedness of concepts. The method relies solely on the structure of a conceptual network and eliminates the need for performing additional corpus analysis. The network structure is employed to generate artificial conceptual glosses. They replace textual definitions proper written by humans and are processed by a dictionary based metric of semantic relatedness 1. We implemented the metric on the basis of GermaNet, the German counterpart of WordNet, and evaluated the results on a German dataset of 57 word pairs rated by human subjects for their semantic relatedness. Our approach can be easily applied to compute semantic relatedness based on alternative conceptual networks, e.g. in the domain of life sciences.
%@ 3-540-29172-5, 978-3-540-29172-5
@inproceedings{gurevych2005using,
abstract = {We present a new method for computing semantic relatedness of concepts. The method relies solely on the structure of a conceptual network and eliminates the need for performing additional corpus analysis. The network structure is employed to generate artificial conceptual glosses. They replace textual definitions proper written by humans and are processed by a dictionary based metric of semantic relatedness [1]. We implemented the metric on the basis of GermaNet, the German counterpart of WordNet, and evaluated the results on a German dataset of 57 word pairs rated by human subjects for their semantic relatedness. Our approach can be easily applied to compute semantic relatedness based on alternative conceptual networks, e.g. in the domain of life sciences.},
acmid = {2145986},
added-at = {2017-12-10T12:30:43.000+0100},
address = {Berlin, Heidelberg},
author = {Gurevych, Iryna},
biburl = {https://www.bibsonomy.org/bibtex/21b05f299b81522fd0f24357c0ddebcb7/thoni},
booktitle = {Proceedings of the Second International Joint Conference on Natural Language Processing},
description = {Using the structure of a conceptual network in computing semantic relatedness},
doi = {10.1007/11562214_67},
interhash = {adeb9934963b60eeb912581772cb97d2},
intrahash = {1b05f299b81522fd0f24357c0ddebcb7},
isbn = {3-540-29172-5, 978-3-540-29172-5},
keywords = {conceptual network relatedness semantic wordnet},
location = {Jeju Island, Korea},
numpages = {12},
pages = {767--778},
publisher = {Springer-Verlag},
series = {IJCNLP'05},
timestamp = {2017-12-10T12:30:43.000+0100},
title = {Using the Structure of a Conceptual Network in Computing Semantic Relatedness},
url = {http://dx.doi.org/10.1007/11562214_67},
year = 2005
}