by Ted Pedersen, Serguei V S Pakhomov, Siddharth Patwardhan, Christopher G Chute
Abstract:
Measures of semantic similarity between concepts are widely used in Natural Language Processing. In this article, we show how six existing domain-independent measures can be adapted to the biomedical domain. These measures were originally based on WordNet, an English lexical database of concepts and relations. In this research, we adapt these measures to the SNOMED-CT ontology of medical concepts. The measures include two path-based measures, and three measures that augment path-based measures with information content statistics from corpora. We also derive a context vector measure based on medical corpora that can be used as a measure of semantic relatedness. These six measures are evaluated against a newly created test bed of 30 medical concept pairs scored by three physicians and nine medical coders. We find that the medical coders and physicians differ in their ratings, and that the context vector measure correlates most closely with the physicians, while the path-based measures and one of the information content measures correlates most closely with the medical coders. We conclude that there is a role both for more flexible measures of relatedness based on information derived from corpora, as well as for measures that rely on existing ontological structures.
Reference:
Measures of semantic similarity and relatedness in the biomedical domain. (Ted Pedersen, Serguei V S Pakhomov, Siddharth Patwardhan, Christopher G Chute), In Journal of biomedical informatics, volume 40, 2007.
Bibtex Entry:
@article{Pedersen2007,
abstract = {Measures of semantic similarity between concepts are widely used in Natural Language Processing. In this article, we show how six existing domain-independent measures can be adapted to the biomedical domain. These measures were originally based on WordNet, an English lexical database of concepts and relations. In this research, we adapt these measures to the SNOMED-CT ontology of medical concepts. The measures include two path-based measures, and three measures that augment path-based measures with information content statistics from corpora. We also derive a context vector measure based on medical corpora that can be used as a measure of semantic relatedness. These six measures are evaluated against a newly created test bed of 30 medical concept pairs scored by three physicians and nine medical coders. We find that the medical coders and physicians differ in their ratings, and that the context vector measure correlates most closely with the physicians, while the path-based measures and one of the information content measures correlates most closely with the medical coders. We conclude that there is a role both for more flexible measures of relatedness based on information derived from corpora, as well as for measures that rely on existing ontological structures.},
author = {Pedersen, Ted and Pakhomov, Serguei V S and Patwardhan, Siddharth and Chute, Christopher G},
doi = {10.1016/j.jbi.2006.06.004},
issn = {1532-0480},
journal = {Journal of biomedical informatics},
keywords = {Computerized,Controlled,Database Management Systems,Databases,Factual,Forms and Records Control,Humans,Information Storage and Retrieval,Language,Medical Informatics,Medical Informatics: methods,Medical Records Systems,Natural Language Processing,SML-LIB-BIBLIO,SSM\_comparison,Semantic Similarity,Semantics,Software,Systematized Nomenclature of Medicine,Terminology as Topic,Vocabulary,lang:ENG},
mendeley-tags = {SML-LIB-BIBLIO,SSM\_comparison,Semantic Similarity,lang:ENG},
month = jun,
number = {3},
pages = {288--99},
pmid = {16875881},
title = {{Measures of semantic similarity and relatedness in the biomedical domain.}},
url = {http://www.ncbi.nlm.nih.gov/pubmed/16875881},
volume = {40},
year = {2007}
}