What is the default nltk part of speech tagset?

Question

While experimenting with NLTK part of speech tagging, I noticed a lot of VBP tags in the output of my calls to nltk.pos_tag. I noticed this tag is not in the Brown Corpus part of speech tagset. It is however a part of the UPenn tagset.

What tagset does nltk use by default? I can't find this in the official documentation or the apidocs.

Answer 1

Ntlk uses PennTreebank tagset . Have a look at this link http://nltk.org/api/nltk.tag.html