You are here
A Systematic Approach for Automatically Generating Derivational Variants in Lexical Tools Based on theSPECIALIST Lexicon
The demand for natural language processing (NLP) in medicine has grown significantly in recent years. This growth is expected to increase rapidly due to the continuing adoption of electronic medical records (EMRs). Medical language processing (MLP) seeks to analyze linguistic patterns found not only in electronic medical records, but also in published biomedical research, clinical trials reports, and other sources. Due to the great deal of lexical variation in natural language, managing this variability is an important key to successful MLP1-2. The National Library of Medicine (NLM) distributes the NLP SPECIALIST Lexicon and Lexical Tools as one of the Unified Medical Language System (UMLS) Knowledge Sources along with the Metathesaurus to provide the NLP/MLP community with rich NLP resources and an extensive NLP toolset since 19943. One of these SPECIALIST tools, Lexical Variant Generation (LVG), is designed to handle lexical variations including derivational variant generation. This paper presents a novel systematic approach to the automatic generation of derivational variants using this tool in conjunction with the SPECIALIST Lexicon.