All IT Courses 50% Off
Artificial Intelligence Tutorials

Part of Speech (POS) Tagging and Chunking with NLTK

What is Part of Speech

A part of speech POS Tagging is a classification system in the English Language that reveals the role a word plays in a context. There are eight parts of speech in the English Language: nouns, pronouns, verbs, adverbs, adjectives, prepositions, conjunctions, and interjections.

  • Nouns are the name of places, animals, persons or things and examples include Tokyo, Elephant, Mike, vehicle 
  • Pronouns are words that replace a noun and examples include he, she, they, her, him, etc 
  • Verbs are action words are example include go, eat, drive, write, sleep, etc
  • Adverbs are words that further describes a verb, adjective or another and example include quickly, boldly, often, poorly, yearly, etc
  • Adjectives are words that further describes a noun or pronoun and example include quick, angry, new, cheerful, yellow, etc
  • Propositions are words that relate nouns or pronouns with other words and examples include in, at, on, for, under, above, etc
  • Conjunctions are words used to join words or phrases in a sentence and examples include and, while, but, nevertheless, because, etc
  • Interjections are words used to convey emotions or surprises and examples include Wow, Really, Hurrah, Oh, Alas, etc. 

Now that you know what each part of speech are, let’s discuss Part of Speech Tagging 

Part of Speech (POS) Tagging 

POS tagging in simple terms means allocating every word in a sentence to a part of speech. NLTK has a method called pos_tag that performs POS tagging on a sentence. The methods apply supervised learning approaches that utilize features such as context, the capitulation of words, punctuations, and so on to determine the part of speech. 

POS tagging is a critical procedure to understand the meaning of a sentence and know the relationship between words. 

There are 35 POS tags in NLTK’s pos_tag methods. The tags are shown in the table below

TagAbbreviation Words
Coordinating Conjunction CCBut, yet, although
Determiner DTA, An, The, This, My, Most
Cardinal DigitCDOne, Two, Three, Forty
Existential ThereEXThere
Foreign WordFWEn masse, bona fide, et cetera, et al
Subordinating Conjunction or PrepositionINOver, Behind, Into
AdjectiveJJBeautiful, Slow, New
Adjective, Comparative JJRGreater, Better, Older
Adjective, SuperlativeJJSGreatest, Best, Oldest
List MarkerLSi, ii, iii, iv, … 
ModalMDHave, Can, Shall
Noun, SingularNNSchool, Table, Pen
Noun, PluralNNSSchools, Tables, Pens
Proper Noun, Singular NNPMonday, Chicago, Mark
Proper Noun, Plural NNPSKoreans, Universities, Americans 
Predeterminer PDTBoth, All, The
Possessive Endings POSDavid’s, Dan’s, Francis’
Personal PronounPRPI, They, She
Possessive PronounPRP$His, Her, Their
AdverbRBLater, Very, Already
Adverb, ComparativeRBRBetter, More, Worse
Adverb, SuperlativeRBSBest, Most, Worst
Particle RPAt, Across, About
Verb, Base FormVBJump, Eat, Play
Verb, Past TenseVBD Jumped, Ate, Played 
Verb, Present Participle VBGJumping, Eating, Playing
Verb, Past Participle VBNTaken, Given, Gone
Verb, Present Tense but not Third Person SingularVBPEnd, Go, Endure
Verb, Present Tense, Third Person Singular VBZJumps, Eats, Plays
Wh – Determiner WDTWhich, What, Whichever
Wh – PronounsWP Which, Whom, What
Possessive Wh – Pronoun WP$Whose
Wh – Adverb WRBWhere, Why, When

Now that you know what the POS tags are, let’s take a code example to demonstrate the steps involved in POS tagging

#import the nltk library
import nltk
#define a text
sentence = "The man was excited after he was informed about his promotion at work"
#tokenize the text
tokens = nltk.word_tokenize(sentence)

#Perform POS tagging


[('The', 'DT'),
 ('man', 'NN'),
 ('was', 'VBD'),
 ('excited', 'VBN'),
 ('after', 'IN'),
 ('he', 'PRP'),
 ('was', 'VBD'),
 ('informed', 'VBN'),
 ('about', 'IN'),
 ('his', 'PRP$'),
 ('promotion', 'NN'),
 ('at', 'IN'),
 ('work', 'NN')]

You can also check for more information about a tag using the help.upenn_tagset() method. Say I have forgotten what JJ means, I can find out by typing this line of code"JJ")


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 ...

The code informs us that JJ means ‘adjective’ and went on to list some examples.


Chunking can be defined as the process of extracting phrases or chunks of texts from unstructured texts. There are situations where a single word cannot encapsulate the complete meaning of a text. In such cases, chunks can be used to extract meaningful insights. In other words, chunking allows more flexibility in the extraction process.  

Chunking works on top of POS tags such that it takes input from the POS tags and outputs the chunks. A common group of chunk tags is the noun phrase chunk (NP chunk). To create a noun phrase chunk, a chunk grammar is first defined using POS tags. This chunk grammar contains the rule with which the chunks would be created. 

The rule is created using regular expressions and the following syntax

? means match 0 or 1 repetitions 
* means match 0 or more repetitions
+ means match 1 or more
. means any character but not a new line

The POS tags and regular expressions are placed inside the < > placeholders. <RB.?> for instance would mean 0 or more of any adverbial tense. Let’s take a coding example to drive home our point.

#import the library
import nltk
#define the text
sentence = "I told the children I was going to tell them a story. They were excited"
#tokenize the text
tokens = nltk.word_tokenize(sentence)
#perform POS tagging
tags = nltk.pos_tag(tokens)
#define a chunk grammar named mychunk
chunk_grammar = """ mychunk: {<NNS.?>*<PRP.?>*<VBD?>}"""
#parse the grammar with regular expression parser
parser = nltk.RegexpParser(chunk_grammar)
#assign the chunk
tree = parser.parse(tags)

After getting the POS tags, the chunk grammar defined would select plural nouns with not more than 1 repetition, followed by personal pronouns with not more than 1 repetition, followed by the past tense verb with not more than 1 repetition, anywhere in the text. A RegexpParser was used to parse the chunk grammar. The POS tags were parsed with the parse() method to print the chunk. See the out output.


  (mychunk I/PRP told/VBD)
  (mychunk children/NNS I/PRP was/VBD)
  (mychunk tell/VB)
  (mychunk They/PRP were/VBD)

As seen, “I told”, “Children I was”, “Tell” and “They were” were the selected chunk. To visualize the results better, you can use draw() method



  (mychunk I/PRP told/VBD)
  (mychunk children/NNS I/PRP was/VBD)
  (mychunk tell/VB)
  (mychunk They/PRP were/VBD)
(mychunk I/PRP told/VBD)
(mychunk children/NNS I/PRP was/VBD)
(mychunk tell/VB)
(mychunk They/PRP were/VBD)

Part of Speech (POS) Tagging and Chunking with NLTK

Why is Chunking Important

Chunking can be used for entity detection. It can be used to extract word patterns from a large text without necessarily analyzing the entire text. Say you have a very large text and you only need to extract information such as name, item bought, and price of the item and the date. You can define a chunk grammar and use chunking to detect this pattern and extract the information quickly. 

In summary, while it is good to use POS tagging to understand the role of a word in a sentence. Chunking helps to identify and understand phrases in a sentence and can perform rapid word filtering based on some defined grammar.

Facebook Comments

Leave a Reply

Your email address will not be published. Required fields are marked *

This site uses Akismet to reduce spam. Learn how your comment data is processed.

Related Articles

Back to top button

Get Python Course
worth 499$ for FREE!

Offer valid for 1st 20 seats only, Hurry up!!

You have successfully subscribed to the newsletter

There was an error while trying to send your request. Please try again.

H2kinfosys Blog will use the information you provide on this form to be in touch with you and to provide updates and marketing.