When using a parser or for any question in Annotation in Core NLP, is there a way to access the probability or limit of error?
To put my question in context, I'm trying to figure out if there is a way to programmatically detect a case of ambiguity. For example, in the sentence below, the verb desire is defined as a noun. I would like to be able to know such a measure that I can get or calculate from Core NLP APi to say that there can be ambiguity.
(NP (NP (NNP Whereas)) (, ,) (NP (NNP users) (NN desire) (S (VP (TO to) (VP (VB sell))))))
Chris
source share