explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-02-03 13:14:11 +03:00
Code Issues Packages Projects Releases Wiki Activity

Return lowercase form as default except for PROPN

Browse Source
This commit is contained in:
Adriane Boyd 2020-05-20 15:35:08 +02:00
parent 4fa9670537
commit 8cba0e41d8
1 changed files with 5 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
spacy/lemmatizer.py
View File

@ -56,6 +56,11 @@ class Lemmatizer(object):
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", {})
if not any((index_table.get(univ_pos), exc_table.get(univ_pos), rules_table.get(univ_pos))):
if univ_pos == "propn":
return [string]
else:
return [string.lower()]
lemmas = self.lemmatize( lemmas = self.lemmatize(
string, string,
index_table.get(univ_pos, {}), index_table.get(univ_pos, {}),