Measuring the similarity and relatedness of concepts in the medical domain: IHI 2012 tutorial overview

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Scopus citations

Abstract

The ability to quantify the degree to which concepts are similar or related to each other is a key component in many Natural Language Processing (NLP) and Artificial Intelligence (AI) applications. For example, in a document search application, it can be very useful to identify text snippets that contain terms that are similar to (but not identical) to those provided by a user. This tutorial will introduce the theory behind measures of semantic similarity and relatedness, and show how these can be applied in the medical domain by using freely-available open-source software1 (UMLS::Similarity). This software takes advantage of the Unified Medical Language System2 (UMLS), which is maintained by the National Library of Medicine (USA). The tutorial will also show how to evaluate existing measures with manually-created reference standards.

Original languageEnglish (US)
Title of host publicationIHI'12 - Proceedings of the 2nd ACM SIGHIT International Health Informatics Symposium
Pages879
Number of pages1
DOIs
StatePublished - 2012
Event2nd ACM SIGHIT International Health Informatics Symposium, IHI'12 - Miami, FL, United States
Duration: Jan 28 2012Jan 30 2012

Publication series

NameIHI'12 - Proceedings of the 2nd ACM SIGHIT International Health Informatics Symposium

Other

Other2nd ACM SIGHIT International Health Informatics Symposium, IHI'12
Country/TerritoryUnited States
CityMiami, FL
Period1/28/121/30/12

Keywords

  • Algorithms
  • Experimentation

Fingerprint

Dive into the research topics of 'Measuring the similarity and relatedness of concepts in the medical domain: IHI 2012 tutorial overview'. Together they form a unique fingerprint.

Cite this