python nltk pos_tags词性标签说明

用法：

pos_tags = nltk.pos_tag(words)
words是独立的单词列表

举个栗子

处理一段英文文本（text），进行分词，删除停用词，词性识别。

import nltk
from nltk.tokenize import sent_tokenize, word_tokenize
from nltk.corpus import stopwords
from string import punctuation

text = 'Compatibility of systems of linear constraints over the set of natural numbers.'
# 分词
words_before = word_tokenize(text.lower())

# 删除停用词和标点符号
stopwords = set(stopwords.words('english') + list(punctuation))

words = []
for w in words_before:
    if w not in stopwords:
        words.append(w)

# 词性标注
pos_tags = nltk.pos_tag(words)
print(pos_tags)

输出

[('compatibility', 'NN'), ('systems', 'NNS'), ('linear', 'JJ'), ('constraints', 'NNS'), ('set', 'VBD'), ('natural', 'JJ'), ('numbers', 'NNS')]

标签说明：

标签	原词	含义	举例
CC	coordinatingconjunction	连词	and, or,but, if, while,although
CD	cardinaldigit	数词	twenty-four, fourth, 1991,14:24
DT	determiner	限定词	the, a, some, most,every, no
EX	existentialthere	存在量词	there, there’s
FW	foreignword	外来词	dolce, ersatz, esprit, quo,maitre
IN	preposition/subordinating conjunction	介词连词	on, of,at, with,by,into, under
JJ	adjective	形容词	new,good, high, special, big, local
JJR	adjective comparative	形容词比较级	bleaker braver breezier briefer brighter brisker
JJS	adjective, superlative	形容词最高级	calmest cheapest choicest classiest cleanest clearest
LS	listmarker	标记
MD	modal	情态动词	can cannot could couldn’t
NN	noun , singular	名词	year,home, costs, time, education
NNS	nounplural	名词复数	undergraduates scotches
NNP	propernoun, singular	专有名词	Alison,Africa,April,Washington
NNPS	proper noun, plural	专有名词复数	Americans Americas Amharas Amityvilles
PDT	predeterminer	前限定词	all both half many
POS	possessiveending	所有格标记	’ 's
PRP	personalpronoun	人称代词
PRP$	possessive pronoun	所有格	her his mine my our ours
RB	adverb	副词	occasionally unabatingly maddeningly
RBR	adverb,comparative	副词比较级	further gloomier grander
RBS	adverb,superlative	副词最高级	best biggest bluntest earliest
RP	particle	虚词	aboard about across along apart
SYM		符号	% & ’ ‘’ ‘’. ) )
TO	to	词	to to
UH	interjection	感叹词	Goodbye Goody Gosh Wow
VB	verb, baseform	动词	ask assemble assess
VBD	verb, pasttense	动词过去式	dipped pleaded swiped
VBG	verb,gerund/present participle	动词现在分词	telegraphing stirring focusing
VBN	verb, pastparticiple	动词过去分词	multihulled dilapidated aerosolized
VBP	verb,sing. present, non-3d	动词现在式非第三人称时态	predominate wrap resort sue
VBZ	verb, 3rdperson sing. present	动词现在式第三人称时态	bases reconstructs marks
WDT	wh-determiner	Wh限定词	who,which,when,what,where,how
WP	wh-pronoun	WH代词	that what whatever
WP$	possessivewh-pronoun	WH代词所有格	whose
WRB	wh-abverb	WH副词	-