You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Lemmas are not defined for WordNet, so I had to make up the policy. I decided to do it this way. Otherwise you'd have to guess what "she", "they", "it" etc resolved to.
In a lot of other WordNet lemmatizers, "his" gets lemmatized to "hi", because it's not in the lexicon!
No sure if this is a bug or a feature, but just thought I would note it:
>>>tokens = nlp(u"I see you.", tag=True, parse=False)
>>>tokens[0].lemma_
'-PRON-'
>>>tokens[2].lemma_
'-PRON-'
Shouldn't the lemmas be "I" and "you"?
Thanks for the nice work on spaCy!
-Cyrus
The text was updated successfully, but these errors were encountered: