Spaces:
Sleeping
Sleeping
File size: 1,655 Bytes
d916065 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 |
# Natural Language Toolkit: WordNet stemmer interface
#
# Copyright (C) 2001-2023 NLTK Project
# Author: Steven Bird <[email protected]>
# Edward Loper <[email protected]>
# URL: <https://www.nltk.org/>
# For license information, see LICENSE.TXT
from nltk.corpus import wordnet as wn
class WordNetLemmatizer:
"""
WordNet Lemmatizer
Lemmatize using WordNet's built-in morphy function.
Returns the input word unchanged if it cannot be found in WordNet.
>>> from nltk.stem import WordNetLemmatizer
>>> wnl = WordNetLemmatizer()
>>> print(wnl.lemmatize('dogs'))
dog
>>> print(wnl.lemmatize('churches'))
church
>>> print(wnl.lemmatize('aardwolves'))
aardwolf
>>> print(wnl.lemmatize('abaci'))
abacus
>>> print(wnl.lemmatize('hardrock'))
hardrock
"""
def lemmatize(self, word: str, pos: str = "n") -> str:
"""Lemmatize `word` using WordNet's built-in morphy function.
Returns the input word unchanged if it cannot be found in WordNet.
:param word: The input word to lemmatize.
:type word: str
:param pos: The Part Of Speech tag. Valid options are `"n"` for nouns,
`"v"` for verbs, `"a"` for adjectives, `"r"` for adverbs and `"s"`
for satellite adjectives.
:param pos: str
:return: The lemma of `word`, for the given `pos`.
"""
lemmas = wn._morphy(word, pos)
return min(lemmas, key=len) if lemmas else word
def __repr__(self):
return "<WordNetLemmatizer>"
|