Avoid lemmatizing inappropriate tags in English lemmatizer

2017-10-11 03:23:23 +02:00 · 2017-10-11 03:23:23 +02:00 · c15d8278cb
parent d528b6e36d
commit c15d8278cb
1 changed files with 2 additions and 0 deletions
--- a/spacy/lemmatizer.py
+++ b/spacy/lemmatizer.py
@ -24,6 +24,8 @@ class Lemmatizer(object):
            univ_pos = 'adj'
        elif univ_pos == PUNCT:
            univ_pos = 'punct'
+        else:
+            return set([string.lower()])
        # See Issue #435 for example of where this logic is requied.
        if self.is_base_form(univ_pos, morphology):
            return set([string.lower()])