NLTK的所有可能的pos标签是什么?

Ora*_*Tux 130 python nltk

如何找到包含Natural Language Toolkit(nltk)使用的所有可能pos标记的列表?

phi*_*ler 145

这本书有一个如何寻找标签集帮助的说明,例如:

nltk.help.upenn_tagset()
Run Code Online (Sandbox Code Playgroud)

其他人可能很相似.(注意:也许你首先必须tagsets从下载助手的模型部分下载)

  • 我认为这不是隐藏的问题,这也是我想要标记一个句子的原因,因为我正在寻找nltk将我的动词标记为名词的原因而我不知道不同的标记集可以使用.这对此也有帮助,谢谢! (3认同)
  • 现在我很好奇:这有什么神秘之处?我从来没有真正使用过NLTK,找到答案花了我五分钟的谷歌搜索和搜索......是真的_that_隐藏? (2认同)
  • @phipsgabler 如果其他人像我一样,我的期望是错误的。我期望有一个查找表/列表/映射,将诸如“RB”之类的词首字母缩略词映射到“副词”之类的含义。([这里是一个例子](https://www.geeksforgeeks.org/part-speech-tagging-stop-words-using-nltk-python/);或者参见@Suzana的答案,它链接了[Penn Treebank标签集](https://www.ling.upenn.edu/courses/Fall_2003/ling001/penn_treebank_pos.html))。但你是对的,内置的 `nltk.help.upenn_tagset('RB')` 很有帮助,并且在 [`nltk` 书](https://www.nltk.org/book/ch05.html ), (2认同)

bin*_*max 123

为了节省一些时间,这里是我从一个小语料库中提取的列表.我不知道它是否完整,但它应该包含大部分(如果不是全部)upenn_tagset的帮助定义...

CC:联合,协调

& 'n and both but either et for less minus neither nor or plus so
therefore times v. versus vs. whether yet
Run Code Online (Sandbox Code Playgroud)

CD:数字,基数

mid-1890 nine-thirty forty-two one-tenth ten million 0.5 one forty-
seven 1987 twenty '79 zero two 78-degrees eighty-four IX '60s .025
fifteen 271,124 dozen quintillion DM2,000 ...
Run Code Online (Sandbox Code Playgroud)

DT:确定者

all an another any both del each either every half la many much nary
neither no some such that the them these this those
Run Code Online (Sandbox Code Playgroud)

EX:存在于那里

there
Run Code Online (Sandbox Code Playgroud)

IN:介词或连词,从属

astride among uppon whether out inside pro despite on by throughout
below within for towards near behind atop around if like until below
next into if beside ...
Run Code Online (Sandbox Code Playgroud)

JJ:形容词或数字,序数

third ill-mannered pre-war regrettable oiled calamitous first separable
ectoplasmic battery-powered participatory fourth still-to-be-named
multilingual multi-disciplinary ...
Run Code Online (Sandbox Code Playgroud)

JJR:形容词,比较

bleaker braver breezier briefer brighter brisker broader bumper busier
calmer cheaper choosier cleaner clearer closer colder commoner costlier
cozier creamier crunchier cuter ...
Run Code Online (Sandbox Code Playgroud)

JJS:形容词,最高级

calmest cheapest choicest classiest cleanest clearest closest commonest
corniest costliest crassest creepiest crudest cutest darkest deadliest
dearest deepest densest dinkiest ...
Run Code Online (Sandbox Code Playgroud)

LS:列表项标记

A A. B B. C C. D E F First G H I J K One SP-44001 SP-44002 SP-44005
SP-44007 Second Third Three Two * a b c d first five four one six three
two
Run Code Online (Sandbox Code Playgroud)

MD:模态辅助

can cannot could couldn't dare may might must need ought shall should
shouldn't will would
Run Code Online (Sandbox Code Playgroud)

NN:名词,普通,单数或质量

common-carrier cabbage knuckle-duster Casino afghan shed thermostat
investment slide humour falloff slick wind hyena override subhumanity
machinist ...
Run Code Online (Sandbox Code Playgroud)

NNP:名词,正确,单数

Motown Venneboerger Czestochwa Ranzer Conchita Trumplane Christos
Oceanside Escobar Kreisler Sawyer Cougar Yvette Ervin ODI Darryl CTCA
Shannon A.K.C. Meltex Liverpool ...
Run Code Online (Sandbox Code Playgroud)

NNS:名词,普通,复数

undergraduates scotches bric-a-brac products bodyguards facets coasts
divestitures storehouses designs clubs fragrances averages
subjectivists apprehensions muses factory-jobs ...
Run Code Online (Sandbox Code Playgroud)

PDT:预先确定

all both half many quite such sure this
Run Code Online (Sandbox Code Playgroud)

POS:属性标记

' 's
Run Code Online (Sandbox Code Playgroud)

PRP:代词,个人

hers herself him himself hisself it itself me myself one oneself ours
ourselves ownself self she thee theirs them themselves they thou thy us
Run Code Online (Sandbox Code Playgroud)

PRP $:代词,占有欲

her his mine my our ours their thy your
Run Code Online (Sandbox Code Playgroud)

RB:副词

occasionally unabatingly maddeningly adventurously professedly
stirringly prominently technologically magisterially predominately
swiftly fiscally pitilessly ...
Run Code Online (Sandbox Code Playgroud)

RBR:副词,比较

further gloomier grander graver greater grimmer harder harsher
healthier heavier higher however larger later leaner lengthier less-
perfectly lesser lonelier longer louder lower more ...
Run Code Online (Sandbox Code Playgroud)

苏格兰皇家银行:副词,最高级

best biggest bluntest earliest farthest first furthest hardest
heartiest highest largest least less most nearest second tightest worst
Run Code Online (Sandbox Code Playgroud)

RP:粒子

aboard about across along apart around aside at away back before behind
by crop down ever fast for forth from go high i.e. in into just later
low more off on open out over per pie raising start teeth that through
under unto up up-pp upon whole with you
Run Code Online (Sandbox Code Playgroud)

TO:"to"作为介词或不定式标记

to
Run Code Online (Sandbox Code Playgroud)

UH:感叹词

Goodbye Goody Gosh Wow Jeepers Jee-sus Hubba Hey Kee-reist Oops amen
huh howdy uh dammit whammo shucks heck anyways whodunnit honey golly
man baby diddle hush sonuvabitch ...
Run Code Online (Sandbox Code Playgroud)

VB:动词,基本形式

ask assemble assess assign assume atone attention avoid bake balkanize
bank begin behold believe bend benefit bevel beware bless boil bomb
boost brace break bring broil brush build ...
Run Code Online (Sandbox Code Playgroud)

VBD:动词,过去时

dipped pleaded swiped regummed soaked tidied convened halted registered
cushioned exacted snubbed strode aimed adopted belied figgered
speculated wore appreciated contemplated ...
Run Code Online (Sandbox Code Playgroud)

VBG:动词,现在分词或动名词

telegraphing stirring focusing angering judging stalling lactating
hankerin' alleging veering capping approaching traveling besieging
encrypting interrupting erasing wincing ...
Run Code Online (Sandbox Code Playgroud)

VBN:动词,过去分词

multihulled dilapidated aerosolized chaired languished panelized used
experimented flourished imitated reunifed factored condensed sheared
unsettled primed dubbed desired ...
Run Code Online (Sandbox Code Playgroud)

VBP:动词,现在时,不是第三人称单数

predominate wrap resort sue twist spill cure lengthen brush terminate
appear tend stray glisten obtain comprise detest tease attract
emphasize mold postpone sever return wag ...
Run Code Online (Sandbox Code Playgroud)

VBZ:动词,现在时,第三人称单数

bases reconstructs marks mixes displeases seals carps weaves snatches
slumps stretches authorizes smolders pictures emerges stockpiles
seduces fizzes uses bolsters slaps speaks pleads ...
Run Code Online (Sandbox Code Playgroud)

WDT:WH-determininer

that what whatever which whichever
Run Code Online (Sandbox Code Playgroud)

WP:WH代名词

that what whatever whatsoever which who whom whosoever
Run Code Online (Sandbox Code Playgroud)

WRB:Wh-adverb

how however whence whenever where whereby whereever wherein whereof why
Run Code Online (Sandbox Code Playgroud)

  • 谢谢!这本来应该是选择的答案,因为这比仅仅在你的控制台中找到_type某些东西来回答要更加全面. (4认同)
  • @PALEN缺少什么? (2认同)
  • 缺少:`$`,`''`,`(`,`)`,`,`,` - `,`.`,`:`,`FW`,`NNPS`,`SYM`,`WP $`,[两个反叛].参见`nltk.help.upenn_tagset()`. (2认同)
  • 这里还有一个列表:https://www.ling.upenn.edu/courses/Fall_2003/ling001/penn_treebank_pos.html (2认同)

Suz*_*ana 59

标签集取决于用于训练标记器的语料库.默认标记器nltk.pos_tag()使用Penn Treebank标记集.

在NLTK 2中,您可以检查哪个标记器是默认标记器,如下所示:

import nltk
nltk.tag._POS_TAGGER
>>> 'taggers/maxent_treebank_pos_tagger/english.pickle'
Run Code Online (Sandbox Code Playgroud)

这意味着它是在Treebank语料库上训练的最大熵标记器.

nltk.tag._POS_TAGGER在NLTK 3中不再存在,但文档说明现成的标记器仍然使用Penn Treebank标记集.

  • 谢谢,imo这是一个比被接受的答案更有用的答案. (5认同)
  • 这是一个不完整的答案。首先,`nltk.tag._POS_TAGGER` 不会执行,也没有提供关于导入内容的具体说明。此外,找出正在使用的标记器是答案的一半,问题是要求获取标记器中所有可能标记的列表 (3认同)
  • 它是语料库而不是标记符来确定标记集.只要您知道语料库名称,完整的标记集就只能在Google上搜索. (3认同)

Dou*_*ore 32

以下内容可用于访问由缩写键控的dict:

>>> from nltk.data import load
>>> tagdict = load('help/tagsets/upenn_tagset.pickle')
>>> tagdict['NN'][0]
'noun, common, singular or mass'
>>> tagdict.keys()
['PRP$', 'VBG', 'VBD', '``', 'VBN', ',', "''", 'VBP', 'WDT', ...
Run Code Online (Sandbox Code Playgroud)

  • 我更喜欢这种方法,而不是公认的解决方案,因为它更简单并且清楚地列举了可能的值 (2认同)

mdu*_*bez 26

该参考资料可在官方网站上获得

从那里复制和粘贴:

  • CC | 协调连接|
  • CD | 基数|
  • DT | 确定者|
  • EX | 存在的那里 |
  • FW | 外国词|
  • IN | 介词或从属连词|
  • JJ | 形容词|
  • JJR | 形容词,比较|
  • JJS | 形容词,最高级的
  • LS | 列表项目标记|
  • MD | 莫代尔|
  • NN | 名词,单数或质量|
  • NNS | 名词,复数|
  • NNP | 专有名词,单数|
  • NNPS | 正确的名词,复数|
  • PDT | 预定义者|
  • POS | 占有结束|
  • PRP | 人称代词|
  • PRP $ | 占有代词|
  • RB | 副词|
  • RBR | 副词,比较|
  • RBS | 副词,最高级的
  • RP | 粒子|
  • SYM | 符号|
  • TO | |
  • UH | 感叹词|
  • VB | 动词,基本形式|
  • VBD | 动词,过去式|
  • VBG | 动词,动名词或现在分词|
  • VBN | 动词,过去分词|
  • VBP | 动词,非第三人称单数礼物|
  • VBZ | 动词,第3人单数礼物|
  • WDT | Wh-determininer |
  • WP | Wh-pronoun |
  • WP $ | 拥有wh代名词|
  • WRB | Wh-adverb |