explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-25 17:36:30 +03:00
Code Issues Packages Projects Releases Wiki Activity

define German dummy lemmatizer until morphology is done

Browse Source
This commit is contained in:
Wolfgang Seeker 2016-05-02 16:04:53 +02:00
parent 6e1f1c4b9e
commit dae6bc05eb
2 changed files with 11 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
bin/parser/train.py
View File

@ -111,8 +111,6 @@ def train(Language, gold_tuples, model_dir, n_iter=15, feat_set=u'basic',
gold_tuples = gold_tuples[:n_sents]
nlp = Language(data_dir=model_dir, tagger=False, parser=False, entity=False)
if nlp.lang == 'de':
nlp.vocab.morphology.lemmatizer = lambda string,pos: set([string])
nlp.tagger = Tagger.blank(nlp.vocab, Tagger.default_templates())
nlp.parser = Parser.from_dir(dep_model_dir, nlp.vocab.strings, ArcEager)
nlp.entity = Parser.from_dir(ner_model_dir, nlp.vocab.strings, BiluoPushDown)

11
spacy/de/__init__.py
View File

@ -3,7 +3,18 @@ from __future__ import unicode_literals, print_function
from os import path
from ..language import Language
from ..vocab import Vocab
from .. import attrs
from .. import util
from .. import about
class German(Language):
lang = 'de'
@classmethod
def default_vocab(cls, package, get_lex_attr=None, vectors_package=None):
vocab = super(German,cls).default_vocab(package,get_lex_attr,vectors_package)
# for now until the morphology is done for German
vocab.morphology.lemmatizer = lambda string,pos: set([string])
return vocab