“Lemmatisierung in NLP” Code-Antworten

Lemmatisierung in NLP

# Lemmatize with POS Tag
from nltk.corpus import wordnet

def get_wordnet_pos(word):
    """Map POS tag to first character lemmatize() accepts"""
    tag = nltk.pos_tag([word])[0][1][0].upper()
    tag_dict = {"J": wordnet.ADJ,
                "N": wordnet.NOUN,
                "V": wordnet.VERB,
                "R": wordnet.ADV}

    return tag_dict.get(tag, wordnet.NOUN)


# 1. Init Lemmatizer
lemmatizer = WordNetLemmatizer()

# 2. Lemmatize Single Word with the appropriate POS tag
word = 'feet'
print(lemmatizer.lemmatize(word, get_wordnet_pos(word)))