def fromTokensToPOS(tokens, lang='en'): tagger_ = get_pos_tagger(lang='en') nlp = spacy.load('en') doc = nlp.tokenizer.tokens_from_list(tokens) tags = nlp.tagger(doc) pos = list() for i, k in enumerate(tagger_.annotate(tokens)): pos.append([k[1], tags[i].pos_]) return pos
def pos_tagger(self): return get_pos_tagger(lang=self.language.code)