Unexpected lemma: "inner" -> "inn"

[davechallis]

I've previously (in other lemmatization software) seen "inner" -> "inner" (but again, not sure what correct lemma is, only that "inn" seems wrong here).

I did notice some tasks for improving lemmatization in Spacy in future though, so can hold off on reporting lemmatization issues if it's not helpful at the moment.

Example case:

import spacy
nlp = spacy.load('en')
for token in nlp("Wearing inners in the innermost inner space in the inn."):
    print(token, token.lemma_)

Output:

Wearing wear
inners inner
in in
the the
innermost innermost
inner inn
space space
in in
the the
inn inn
. .

Info about spaCy

• spaCy version: 1.7.2
• Platform: Darwin-16.4.0-x86_64-i386-64bit
• Python version: 3.6.0
• Installed models: en

[honnibal]

Thanks, that's definitely wrong.

[lock]

This thread has been automatically locked since there has not been any recent activity after it was closed. Please open a new issue for related bugs.