def snowball_stem(word, lang='english'):
global _nltk_snowball_stemmer
try:
_nltk_snowball_stemmer
except NameError:
available_languages = ['danish', 'dutch', 'english', 'finnish', 'french',
'german', 'german2', 'hungarian', 'italian',
'kraaij_pohlmann', 'lovins', 'norwegian',
'porter', 'portuguese', 'romanian', 'russian',
'spanish', 'swedish', 'turkish']
assert lang in available_languages, "Snowball Stemmer for {} not available".format(lang)
# Checks that the snowball data was previously downloaded.
download('snowball_data', quiet=True)
_nltk_snowball_stemmer = SnowballStemmer(lang)
return _nltk_snowball_stemmer.stem(word)
评论列表
文章目录