Tokenizing words in German

user_17067836 0
Viewed 289

I am trying to determine the subject in a German sentence. For English I used to do:

import spacy
nlp = spacy.load('en')
sent = "I shot an elephant"
doc=nlp(sent)

sub_toks = [tok for tok in doc if (tok.dep_ == "nsubj") ]

print(sub_toks)

But it doesn't work for nlp = spacy.load('de_core_news_sm') and using a German sentence. It returns an empty list.

I tried looking here, even if they have parts of speech instead of subject, object etc. But it returns empty lists too. Is this even possible in German?

tokenize nlp text python
1 Answers

try this snippet:

sentences inside the module spacy gives you examples for sentences in german

import spacy
from spacy.lang.de.examples import sentences 

nlp = spacy.load("de_core_news_sm")
doc = nlp(sentences[0])
print(doc.text)
for token in doc:
    print(token.text, token.pos_, token.dep_)

See https://spacy.io/models/de

user_176748490
Related