Skip to main content
. 2015 Jun 29;6:29. doi: 10.1186/s13326-015-0026-0

Table 2.

Token-specific orthographic features extracted by regular expressions

Name Description
isAcronym token is an acronym
containsAllCaps all the letters in the token are capitalised
isCapitalised token is capitalised
containsCapLetter token contains at least one capital letter
containsDigits token contains at least one digit
isAllDigits token is made up of digits only