Part-of-speech tagging in NLP - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to import the NLTK library for part-of-speech tagging.

NLP

import nltk

text = "I love learning AI"
tokens = nltk.word_tokenize(text)
pos_tags = nltk.[1](tokens)
print(pos_tags)

Drag options to blanks, or click blank then click option'

AposTag

Btag_pos

Ctagger

Dpos_tag

Attempts:

3 left

💡 Hint

Common Mistakes

Using a wrong function name like tag_pos or posTag.

Forgetting to tokenize the text before tagging.

The correct function to get part-of-speech tags in NLTK is pos_tag().

2fill in blank

medium

Complete the code to tokenize the sentence before tagging.

NLP

sentence = "She enjoys reading books"
tokens = [1](sentence)
print(tokens)

Drag options to blanks, or click blank then click option'

Asentence.split

Bsentence.tokenize

Cnltk.word_tokenize

Dnltk.tokenize_words

Attempts:

3 left

💡 Hint

Common Mistakes

Using sentence.split which does not handle punctuation well.

Using a non-existent function like sentence.tokenize.

The nltk.word_tokenize() function splits the sentence into words (tokens).

3fill in blank

hard

Fix the error in the code to correctly tag the tokens.

NLP

tokens = ['They', 'are', 'playing', 'football']
pos_tags = nltk.pos_tag([1])
print(pos_tags)

Drag options to blanks, or click blank then click option'

Atokens()

Btokens

Ctokens[]

Dtoken

Attempts:

3 left

💡 Hint

Common Mistakes

Calling tokens as a function with parentheses.

Using incorrect syntax like tokens[].

The pos_tag function expects a list of tokens, so pass the variable tokens directly.

4fill in blank

hard

Fill both blanks to create a dictionary of words and their POS tags.

NLP

tokens = ['He', 'runs', 'fast']
pos_tags = nltk.pos_tag(tokens)
pos_dict = [1](pos_tags)
print(pos_dict)

# Access the POS tag of 'runs'
print(pos_dict[[2]])

Drag options to blanks, or click blank then click option'

Adict

B'runs'

C'fast'

Dlist

Attempts:

3 left

💡 Hint

Common Mistakes

Using list() instead of dict() to convert.

Accessing dictionary with wrong key like 'fast'.

Use dict() to convert list of tuples to dictionary, then access the word 'runs' to get its tag.

5fill in blank

hard

Fill the blanks to filter and print only nouns from the tagged tokens.

NLP

tokens = nltk.word_tokenize("Dogs bark loudly at night")
pos_tags = nltk.pos_tag(tokens)
nouns = [word for word, tag in pos_tags if tag [1] [2]]
print(nouns)

# Expected output: ['Dogs', 'night']

Drag options to blanks, or click blank then click option'

A==

Bin

CNN

D['NN', 'NNS']

Attempts:

3 left

💡 Hint

Common Mistakes

Using '==' to compare tag with a list (causes error).

Using wrong tag names or not filtering nouns.

Use 'in' to check if tag is in the list ['NN', 'NNS'] which are noun tags. 'NN' is a noun tag example.