Evaluation of semantic similarity metrics applied to the automatic retrieval of medical documents: An UMLS approach
作者：
Highlights：
• We assess the implication of the correct parameterization of the UMLS Metathesaurus.
• We propose a retrieval system for medical documents represented by UMLS concepts.
• We assess the main semantic similarity metrics in a context based on medical records.
• Using simple metrics in real-life contexts provides a best performance.
摘要
•We assess the implication of the correct parameterization of the UMLS Metathesaurus.•We propose a retrieval system for medical documents represented by UMLS concepts.•We assess the main semantic similarity metrics in a context based on medical records.•Using simple metrics in real-life contexts provides a best performance.
论文关键词：Semantic similarity,Information retrieval,Electronic Health Record,UMLS
论文评审过程：Received 21 April 2015, Revised 27 August 2015, Accepted 19 September 2015, Available online 28 September 2015, Version of Record 10 November 2015.
论文官网地址：https://doi.org/10.1016/j.eswa.2015.09.028
