Skip to main content
. Author manuscript; available in PMC: 2016 Aug 8.
Published in final edited form as: J Biomed Inform. 2015 Jul 22;58(Suppl):S53–S59. doi: 10.1016/j.jbi.2015.06.029

Table 1.

Example of a rule. Row 2 shows a rule for capturing Street mentions. The rule contains four types of components (pattern, orthographic indicators and semantic/lexical and contextual clues).

Feature type Pattern Orthographic Semantic/Lexical Contextual
{RegEx} = [1-9][0-9]{0,3} {ORTHO} = {upperInitial, allCapital, ...} {STREET_CLUE} = {Street, St, Drive, Dr, ...} {SYMBOL} = {Ø, ‘.’}
A rule {RegEx} {ORTHO} {STREET_CLUE}{SYMBOL}
In text ... 62 Angora Dr . ...
... 1 Jefferson Road ...
... 55 Bury St ...