explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-07-15 10:42:34 +03:00
Code Issues Packages Projects Releases Wiki Activity

Remove is_base_form from French lemmatizer (#5733)

Browse Source 
Remove English-specific is_base_form from French lemmatizer.
This commit is contained in:
Adriane Boyd 2020-07-09 22:11:13 +02:00 committed by GitHub
parent 3d83721551
commit 923affd091
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 0 additions and 40 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

40
spacy/lang/fr/lemmatizer.py
View File

@ -45,9 +45,6 @@ class FrenchLemmatizer(Lemmatizer):
univ_pos = "sconj" univ_pos = "sconj"
else: else:
return [self.lookup(string)] return [self.lookup(string)]
# See Issue #435 for example of where this logic is requied.
if self.is_base_form(univ_pos, morphology):
return list(set([string.lower()]))
index_table = self.lookups.get_table("lemma_index", {}) index_table = self.lookups.get_table("lemma_index", {})
exc_table = self.lookups.get_table("lemma_exc", {}) exc_table = self.lookups.get_table("lemma_exc", {})
rules_table = self.lookups.get_table("lemma_rules", {}) rules_table = self.lookups.get_table("lemma_rules", {})
@ -59,43 +56,6 @@ class FrenchLemmatizer(Lemmatizer):
) )
return lemmas return lemmas
def is_base_form(self, univ_pos, morphology=None):
"""
Check whether we're dealing with an uninflected paradigm, so we can
avoid lemmatization entirely.
"""
morphology = {} if morphology is None else morphology
others = [
key
for key in morphology
if key not in (POS, "Number", "POS", "VerbForm", "Tense")
]
if univ_pos == "noun" and morphology.get("Number") == "sing":
return True
elif univ_pos == "verb" and morphology.get("VerbForm") == "inf":
return True
# This maps 'VBP' to base form -- probably just need 'IS_BASE'
# morphology
elif univ_pos == "verb" and (
morphology.get("VerbForm") == "fin"
and morphology.get("Tense") == "pres"
and morphology.get("Number") is None
and not others
):
return True
elif univ_pos == "adj" and morphology.get("Degree") == "pos":
return True
elif VerbForm_inf in morphology:
return True
elif VerbForm_none in morphology:
return True
elif Number_sing in morphology:
return True
elif Degree_pos in morphology:
return True
else:
return False
def noun(self, string, morphology=None): def noun(self, string, morphology=None):
return self(string, "noun", morphology) return self(string, "noun", morphology)