Method setHeadednessFromTokens sets the head of this lexical element
if any the tokens of this lexical element participated in the head
of the noun phrase that this lexical element came from.
Method setMetaMapNounPhraseTokenPosition
tags this token with a mapping from this token
to a mapping that the original MetaMap program
would have done.
Method setNormalizedTerm sets the Variant term, lowercased, devoid of
punctuation - this is supposed to match the normalization that was done
to create the normalized string, string sui table.
setNp() -
Method in class gov.nih.nlm.nls.nlp.textfeatures.Phrase
setNp creates the minimal Nps that the mapper will
use to match on.
Method setPartOfHead is a mechanism to set wheather or not this
token is part of a lexicalElement that has been identified by the
parser as the head lexical element of a noun phrase.
setStrings fills in the details of what the original string for this
phrase is to be, it's span, and, if appropriate, what the string looks like
devoid of determiners, and trailing punctuation..
Method stripOffNonTokenTokens
Strip off the things that got artificially
stuck on before, such as the token <SENTENCE_BREAK>
that was artifically put on during section
tokenization when that information was made
obvious from html tags such as <li> or <p>
but where the sentence tokenizer would have
missed it because it was not a normal
English break.
Method stripPossessiveTokens
Strip Posessives from the lexical element ()
This is being done for mapping purposes,
where the index is likewise created
with possessives stripped off.