What are all possible POS tags of NLTK

Navigating the complexities of natural language processing (NLP) often begins with understanding the fundamental building blocks of human language. One such crucial technique is Part-of-Speech (POS) tagging, which involves categorizing words in a text based on their grammatical role. For developers and researchers working with Python, the Natural Language Toolkit (NLTK) stands out as a powerful and widely-used library for this very purpose. A common question that arises for those delving into text analysis is: What are all possible POS tags of NLTK? This question is vital because the accuracy and depth of your text analysis heavily depend on knowing the specific grammatical labels NLTK assigns and how to interpret them. Understanding these tags unlocks a deeper layer of linguistic insight, enabling more sophisticated applications from sentiment analysis to machine translation.

Understanding Part-of-Speech Tagging and NLTK’s Role

Part-of-Speech (POS) tagging is the process of assigning a grammatical category, such as noun, verb, adjective, or adverb, to each word in a given text. This seemingly simple task is foundational for many advanced NLP applications because it provides a structural understanding of sentences that goes beyond mere word recognition. For instance, knowing if “run” is used as a verb (“I run fast”) or a noun (“a long run”) changes its meaning and how it relates to other words.

NLTK, or the Natural Language Toolkit, is a comprehensive library for building Python programs to work with human language data. It provides easy-to-use interfaces to over 50 corpora and lexical resources, along with a suite of text processing libraries for classification, tokenization, stemming, tagging, parsing, and semantic reasoning. When it comes to POS tagging, NLTK typically employs the Penn Treebank tagset, a widely recognized standard in computational linguistics. This tagset, developed for the Penn Treebank project, offers a granular system for categorizing words, providing a rich dataset for training and evaluating NLP models.

The significance of accurate POS tagging cannot be overstated. It acts as a prerequisite for tasks like named entity recognition, which identifies proper nouns such as people, organizations, or locations. Moreover, it aids in disambiguation, helping to resolve cases where a word can have multiple meanings based on its grammatical context. Our team’s extensive experience in data science consistently shows that well-executed POS tagging dramatically improves the precision of subsequent text analysis steps, making it an indispensable tool for anyone working with unstructured text data.

The Comprehensive Penn Treebank Tagset Used by NLTK

NLTK’s default POS tagger leverages the Penn Treebank tagset, which comprises approximately 48 distinct tags, including punctuation marks. This tagset is designed to be comprehensive, covering a broad spectrum of grammatical categories to facilitate detailed syntactic analysis. Understanding these tags is paramount for anyone asking, “What are all possible POS tags of NLTK?” because they form the core vocabulary of NLTK’s linguistic output.

For example, common tags include ‘NN’ for singular nouns, ‘NNS’ for plural nouns, ‘VB’ for base form verbs, ‘VBD’ for past tense verbs, ‘JJ’ for adjectives, and ‘RB’ for adverbs. There are also specific tags for proper nouns (‘NNP’, ‘NNPS’), determiners (‘DT’), prepositions (‘IN’), conjunctions (‘CC’), and many more. Each tag provides a precise label that allows algorithms to infer the role of a word within a sentence. According to a study published in the Proceedings of the 31st Annual Meeting of the Association for Computational Linguistics, the Penn Treebank corpus and its tagset have been foundational for developing robust statistical NLP models.

The Penn Treebank tagset offers a detailed classification system for words, making it an invaluable resource for researchers and developers in natural language processing. These tags enable a deeper understanding of sentence structure, aiding in tasks such as parsing, information extraction, and machine translation by providing standardized grammatical labels for virtually every word type encountered in English text. This standardization ensures consistency across different NLP projects and allows for the comparison and integration of various linguistic analyses. Below is a list of some of the most frequently encountered tags:

NN: Noun, singular or mass (e.g., “dog”, “water”)
NNS: Noun, plural (e.g., “dogs”, “houses”)
NNP: Proper noun, singular (e.g., “John”, “London”)
NNPS: Proper noun, plural (e.g., “Americans”, “Democrats”)
VB: Verb, base form (e.g., “eat”, “run”)
VBD: Verb, past tense (e.g., “ate”, “ran”)
VBG: Verb, gerund or present participle (e.g., “eating”, “running”)
VBN: Verb, past participle (e.g., “eaten”, “run”)
VBP: Verb, non-3rd person singular present (e.g., “eat”, “run”)
VBZ: Verb, 3rd person singular present (e.g., “eats”, “runs”)
JJ: Adjective (e.g., “big”, “red”)
JJR: Adjective, comparative (e.g., “bigger”, “redder”)
JJS: Adjective, superlative (e.g., “biggest”, “reddest”)
RB: Adverb (e.g., “quickly”, “very”)
RBR: Adverb, comparative (e.g., “quicker”, “faster”)
RBS: Adverb, superlative (e.g., “quickest”, “fastest”)
DT: Determiner (e.g., “the”, “a”, “this”)
IN: Preposition or subordinating conjunction (e.g., “in”, “of”, “before”)
CC: Coordinating conjunction (e.g., “and”, “but”, “or”)
PRP: Personal pronoun (e.g., “I”, “he”, “she”)
PRP$: Possessive pronoun (e.g., “my”, “his”, “her”)
TO: to (e.g., “to go”, “to him”)
WDT: Wh-determiner (e.g., “which”, “what”)

WP: Wh- Question & Answer :
How do I find a list with all possible POS tags used by the Natural Language Toolkit (NLTK)?

To save some folks some time, here is a list I extracted from a small corpus. I do not know if it is complete, but it should have most (if not all) of the help definitions from upenn_tagset…

CC: conjunction, coordinating

& 'n and both but either et for less minus neither nor or plus so therefore times v. versus vs. whether yet

CD: numeral, cardinal

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 ...

DT: determiner

all an another any both del each either every half la many much nary neither no some such that the them these this those

EX: existential there

there

IN: preposition or conjunction, subordinating

astride among upon whether out inside pro despite on by throughout below within for towards near behind atop around if like until below next into if beside ...

JJ: adjective or numeral, ordinal

third ill-mannered pre-war regrettable oiled calamitous first separable ectoplasmic battery-powered participatory fourth still-to-be-named multilingual multi-disciplinary ...

JJR: adjective, comparative

bleaker braver breezier briefer brighter brisker broader bumper busier calmer cheaper choosier cleaner clearer closer colder commoner costlier cozier creamier crunchier cuter ...

JJS: adjective, superlative

calmest cheapest choicest classiest cleanest clearest closest commonest corniest costliest crassest creepiest crudest cutest darkest deadliest dearest deepest densest dinkiest ...

LS: list item marker

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

MD: modal auxiliary

can cannot could couldn't dare may might must need ought shall should shouldn't will would

NN: noun, common, singular or mass

common-carrier cabbage knuckle-duster Casino afghan shed thermostat investment slide humour falloff slick wind hyena override subhumanity machinist ...

NNP: noun, proper, singular

Motown Venneboerger Czestochwa Ranzer Conchita Trumplane Christos Oceanside Escobar Kreisler Sawyer Cougar Yvette Ervin ODI Darryl CTCA Shannon A.K.C. Meltex Liverpool ...

NNS: noun, common, plural

undergraduates scotches bric-a-brac products bodyguards facets coasts divestitures storehouses designs clubs fragrances averages subjectivists apprehensions muses factory-jobs ...

PDT: pre-determiner

all both half many quite such sure this

POS: genitive marker

' 's

PRP: pronoun, personal

hers herself him himself hisself it itself me myself one oneself ours ourselves ownself self she thee theirs them themselves they thou thy us

PRP$: pronoun, possessive

her his mine my our ours their thy your

RB: adverb

occasionally unabatingly maddeningly adventurously professedly stirringly prominently technologically magisterially predominately swiftly fiscally pitilessly ...

RBR: adverb, comparative

further gloomier grander graver greater grimmer harder harsher healthier heavier higher however larger later leaner lengthier less- perfectly lesser lonelier longer louder lower more ...

RBS: adverb, superlative

best biggest bluntest earliest farthest first furthest hardest heartiest highest largest least less most nearest second tightest worst

RP: particle

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

TO: “to” as preposition or infinitive marker

to

UH: interjection

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 ...

VB: verb, base form

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 ...

VBD: verb, past tense

dipped pleaded swiped regummed soaked tidied convened halted registered cushioned exacted snubbed strode aimed adopted belied figgered speculated wore appreciated contemplated ...

VBG: verb, present participle or gerund

telegraphing stirring focusing angering judging stalling lactating hankerin' alleging veering capping approaching traveling besieging encrypting interrupting erasing wincing ...

VBN: verb, past participle

multihulled dilapidated aerosolized chaired languished panelized used experimented flourished imitated reunifed factored condensed sheared unsettled primed dubbed desired ...

VBP: verb, present tense, not 3rd person singular

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 ...

VBZ: verb, present tense, 3rd person singular

bases reconstructs marks mixes displeases seals carps weaves snatches slumps stretches authorizes smolders pictures emerges stockpiles seduces fizzes uses bolsters slaps speaks pleads ...

WDT: WH-determiner

that what whatever which whichever

WP: WH-pronoun

that what whatever whatsoever which who whom whosoever

WRB: Wh-adverb

how however whence whenever where whereby whereever wherein whereof why