explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-24 17:06:29 +03:00
Code Issues Packages Projects Releases Wiki Activity

German lemmatizer additions (#2529)

Browse Source 
* lemma of was-> was

* added new pairs issue @2486

* added article tests
This commit is contained in:
Duygu Altinok 2018-07-09 11:10:15 +02:00 committed by Matthew Honnibal
parent c21efea9bb
commit 00b9a58558
2 changed files with 389 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

387
spacy/lang/de/lemmatizer.py
View File

File diff suppressed because it is too large Load Diff

4
spacy/tests/lang/de/test_lemma.py
View File

@ -7,7 +7,9 @@ import pytest
@pytest.mark.parametrize('string,lemma', [('Abgehängten', 'Abgehängte'), @pytest.mark.parametrize('string,lemma', [('Abgehängten', 'Abgehängte'),
('engagierte', 'engagieren'), ('engagierte', 'engagieren'),
('schließt', 'schließen'), ('schließt', 'schließen'),
('vorgebenden', 'vorgebend')]) ('vorgebenden', 'vorgebend'),
('die', 'der'),
('Die', 'der')])
def test_lemmatizer_lookup_assigns(de_tokenizer, string, lemma): def test_lemmatizer_lookup_assigns(de_tokenizer, string, lemma):
tokens = de_tokenizer(string) tokens = de_tokenizer(string)
assert tokens[0].lemma_ == lemma assert tokens[0].lemma_ == lemma