by Dekang Lin
Abstract:
Similarity is an important and widely used concept. Previous definitions of similarity are tied to a particular application or a form of knowledge representation. We present an informationtheoretic definition of similarity that is applicable as long as there is a probabilistic model. We demonstrate how our definition can be used to measure the similarity in a number of different domains.
Reference:
An Information-Theoretic Definition of Similarity (Dekang Lin), In 15th International Conference of Machine Learning, 1998.
Bibtex Entry:
@inproceedings{Lin1998,
abstract = {Similarity is an important and widely used concept. Previous definitions of similarity are tied to a particular application or a form of knowledge representation. We present an informationtheoretic definition of similarity that is applicable as long as there is a probabilistic model. We demonstrate how our definition can be used to measure the similarity in a number of different domains.},
address = {Madison,WI},
author = {Lin, Dekang},
booktitle = {15th International Conference of Machine Learning},
keywords = {SML-LIB-BIBLIO,lang:ENG,semantic similarity},
mendeley-tags = {SML-LIB-BIBLIO,lang:ENG},
pages = {296--304},
title = {{An Information-Theoretic Definition of Similarity}},
year = {1998}
}