Rooba
/
spaCy
mirror of https://github.com/explosion/spaCy.git
1
1
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Use lookup lemmatizer if lemma unset

This commit is contained in:
Matthew Honnibal 2017-11-18 03:33:31 +01:00
parent db5c714ad2
commit fb26b2cb12
1 changed files with 9 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
spacy/tokens/token.pyx
View File

@ -257,7 +257,11 @@ cdef class Token:
inflectional suffixes. inflectional suffixes.
""" """
def __get__(self): def __get__(self):
return self.c.lemma if self.c.lemma == 0:
lemma = self.vocab.morphology.lemmatizer.lookup(self.orth_)
return lemma
else:
return self.c.lemma
def __set__(self, attr_t lemma): def __set__(self, attr_t lemma):
self.c.lemma = lemma self.c.lemma = lemma
@ -724,7 +728,10 @@ cdef class Token:
with no inflectional suffixes. with no inflectional suffixes.
""" """
def __get__(self): def __get__(self):
return self.vocab.strings[self.c.lemma] if self.c.lemma == 0:
return self.vocab.morphology.lemmatizer.lookup(self.orth_)
else:
return self.vocab.strings[self.c.lemma]
def __set__(self, unicode lemma_): def __set__(self, unicode lemma_):
self.c.lemma = self.vocab.strings.add(lemma_) self.c.lemma = self.vocab.strings.add(lemma_)