Analysis & Design

I. What is LEXICON

The SPECIALIST lexicon is a large syntactic lexicon of biomedical and general English, designed/developed to provide the lexical information needed for the SPECIALIST Natural Language Processing System (NLP) which includes SemRep, MetaMap, the and the Lexical Tools. It is intended to be a general English lexicon that includes many biomedical terms. Coverage includes both commonly occurring English words and biomedical vocabulary. The lexicon entry for each lexical item (word or term) records the syntactic, morphological, and orthographic information needed by the SPECIALIST NLP System.

II. LEXICON and lexical records

A lexical record is a lexicon entry for a word or term records the syntactic, morphological, and orthographic information needed by the SPECIALIST natural language processing system. The lexicon is the data set contains all lexical records.

III. How is LEXICON built?

The SPECIALIST Lexicon has been built since 1994 at National Library of Medicine. A tool called LexBuild was developed to automate and ease the building processes. LexBuild is an extremely important and useful tool for linguists to build the SPECIALIST lexicon and control the quality of LEXICON. In 2004, a centralized web-based tool, LexBuild, is developed to build the SPECIALIST lexicon. This new LexBuild system provides an easier way for building lexicon. It also helps to ensure the quality and completeness of lexical entries and increase lexical coverage. In addition, it's a more robust system for software maintenance. With features of this new LexBuild, the Lexical System group has moved to a new milestone of building Lexicon.

IV. LEXICON release

LEXICON is released annually along with UMLS Metathesaurus. It includes LEXICON, tables generated from LEXICON, Numbers, etc..