nltk中有哪些词性标注器

nltk有如下词性标注器：

import nltk
from nltk.corpus import brown

nltk.data.path = ["C:\\nltk_data\\nltk_data-gh-pages\packages"]
tagged_words = brown.tagged_words(categories='news')
# print(len(tagged_words))
# 100554

tagged_sents = brown.tagged_sents(categories='news')
# print(len(tagged_sents))
# 4623

# 常量标注，所有的词都被标注为相同的Tag
tagger = nltk.DefaultTagger('NN')
print(tagger.evaluate(tagged_sents))
# 0.13089484257215028

# 正则表达式标注
patterns = [(r'.*ing$', 'VBG'), (r'.*ed$', 'VBD'), (r'.*es$', 'VBZ'), (r'.*ould$', 'MD'), \
            (r'.*\'s$', 'NN$'), (r'.*s$', 'NNS'), (r'^-?[0-9]+(.[0-9]+)?$', 'CD'), (r'.*', 'NN')]
tagger = nltk.RegexpTagger(patterns)
print(tagger.evaluate(tagged_sents))
# 0.20326391789486245

# 一元标注器
train_size = int(len(tagged_sents) * 0.8)
print(train_size)
# 3698
tagger = nltk.UnigramTagger(tagged_sents[:train_size])
print(tagger.evaluate(tagged_sents[train_size:]))
# 0.8026879907509996

# 二元标注器
tagger = nltk.BigramTagger(tagged_sents[:train_size])
print(tagger.evaluate(tagged_sents[train_size:]))
# 0.09186376993111421

# 组合多个标注器
t0 = nltk.DefaultTagger('NN')
t1 = nltk.UnigramTagger(tagged_sents[:train_size], backoff=t0)
t2 = nltk.BigramTagger(tagged_sents[:train_size], backoff=t1)
print(t2.evaluate(tagged_sents[train_size:]))
# 0.8360711016908329