N-grams in NLP - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to create bigrams from a list of words.

NLP

words = ['I', 'love', 'machine', 'learning']
bigrams = [(words[i], words[i+[1]]) for i in range(len(words)-1)]
print(bigrams)

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

A1

B2

C3

D0

Attempts:

3 left

💡 Hint

Common Mistakes

Using 2 instead of 1 causes index errors or skips words.

Using 0 pairs the same word with itself.

To create bigrams, we pair each word with the next one, so the index difference is 1.

2fill in blank

medium

Complete the code to generate trigrams from a list of words.

NLP

words = ['deep', 'learning', 'is', 'fun']
trigrams = [(words[i], words[i+1], words[i+[1]]) for i in range(len(words)-2)]
print(trigrams)

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

A3

B1

C0

D2

Attempts:

3 left

💡 Hint

Common Mistakes

Using 1 or 3 causes incorrect grouping or index errors.

Using 0 pairs the same word multiple times.

For trigrams, the third word is two positions ahead of the first, so the index difference is 2.

3fill in blank

hard

Fix the error in the code to correctly generate bigrams.

NLP

words = ['AI', 'is', 'awesome']
bigrams = [(words[i], words[i+[1]]) for i in range(len(words)-1)]
print(bigrams)

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

A0

B2

C1

D-1

Attempts:

3 left

💡 Hint

Common Mistakes

Using range(len(words)) causes index error when accessing words[i+1].

Using index difference other than 1 breaks bigram logic.

The range should stop before the last index to avoid index error; the index difference is 1 for bigrams.

4fill in blank

hard

Fill both blanks to create a dictionary of word counts from a list.

NLP

words = ['data', 'science', 'data', 'AI']
word_counts = {word: words.count([1]) for word in [2]
print(word_counts)

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

Aword

Bwords

Cset(words)

Dlist(words)

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'words' instead of 'word' counts the whole list repeatedly.

Using 'words' instead of 'set(words)' causes duplicate keys.

We count each unique word, so we use 'word' for counting and 'set(words)' to get unique words.

5fill in blank

hard

Fill all three blanks to filter bigrams that start with 'machine'.

NLP

words = ['machine', 'learning', 'is', 'fun']
bigrams = [(words[i], words[i+[1]]) for i in range(len(words)-1)]
filtered = [bigram for bigram in bigrams if bigram[[2]] == [3]]
print(filtered)

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

A1

B0

C'machine'

D'learning'

Attempts:

3 left

💡 Hint

Common Mistakes

Using index 1 checks the second word instead of the first.

Using wrong index difference breaks bigram creation.

Filtering for 'learning' instead of 'machine' changes the result.

The index difference for bigrams is 1; to check the first word in the tuple, use index 0; filter for 'machine'.