Summarization with Hugging Face in NLP - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to load the summarization pipeline from Hugging Face.

NLP

from transformers import pipeline
summarizer = pipeline([1])

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

A"sentiment-analysis"

B"translation"

C"summarization"

D"text-generation"

Attempts:

3 left

💡 Hint

Common Mistakes

Using the wrong pipeline name like "translation" or "text-generation".

Forgetting to put the pipeline name in quotes.

The pipeline for text summarization is called "summarization" in Hugging Face.

2fill in blank

medium

Complete the code to summarize the given text using the summarizer pipeline.

NLP

text = "Machine learning helps computers learn from data."
summary = summarizer([1], max_length=20, min_length=5, do_sample=False)
print(summary[0]['summary_text'])

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

A"text"

Btext

Ctext[0]

Dsummary

Attempts:

3 left

💡 Hint

Common Mistakes

Passing the string "text" instead of the variable text.

Passing summary or text[0] which are incorrect here.

You need to pass the variable 'text' containing the input string to the summarizer.

3fill in blank

hard

Fix the error in the code to correctly print the summary text.

NLP

print(summary[[1]]['summary_text'])

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

A0

B'summary_text'

C1

Dsummary

Attempts:

3 left

💡 Hint

Common Mistakes

Using index 1 which is out of range.

Using a string as index which causes an error.

The summarizer returns a list with one dictionary, so index 0 accesses the first summary.

4fill in blank

hard

Fill both blanks to create a dictionary comprehension that maps each sentence to its summary length.

NLP

sentences = ["AI is fun.", "It helps solve problems."]
summary_lengths = {sentence: len(summary[[1]]['summary_text']) for sentence, summary in [2]

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

A0

B1

Czip(sentences, summaries)

Denumerate(sentences)

Attempts:

3 left

💡 Hint

Common Mistakes

Using enumerate instead of zip which gives wrong pairs.

Using index 1 which is out of range.

Index 0 accesses the summary text in each summary dict. zip(sentences, summaries) pairs sentences with their summaries.

5fill in blank

hard

Fill all three blanks to generate summaries for multiple texts and print each summary.

NLP

texts = ["AI is amazing.", "It changes the world."]
summaries = [summarizer([1], max_length=15, min_length=5, do_sample=False) for [2] in [3]]
for summary in summaries:
    print(summary[0]['summary_text'])

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

Atext

Ctexts

Dsentence

Attempts:

3 left

💡 Hint

Common Mistakes

Using a variable name not defined in the loop.

Passing the whole list instead of each text.

We loop over 'texts' with variable 'text' and summarize each text.