NLP applications in real world - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to load a pre-trained sentiment analysis model using Hugging Face Transformers.

NLP

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

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

A'translation'

B'text-classification'

C'image-classification'

D'speech-recognition'

Attempts:

3 left

💡 Hint

Common Mistakes

Choosing pipelines unrelated to text classification like 'image-classification'.

Using pipeline names meant for other modalities like speech or translation.

The 'text-classification' pipeline is used for sentiment analysis tasks in NLP.

2fill in blank

medium

Complete the code to tokenize input text for a BERT model.

NLP

from transformers import BertTokenizer

tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
tokens = tokenizer.tokenize([1])

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

A'Hello, how are you?'

B12345

C['Hello', 'how', 'are', 'you']

DNone

Attempts:

3 left

💡 Hint

Common Mistakes

Passing a list of words instead of a string.

Passing a number instead of text.

The tokenizer.tokenize method expects a string input representing the text to tokenize.

3fill in blank

hard

Fix the error in the code to correctly perform named entity recognition (NER) using a Hugging Face pipeline.

NLP

from transformers import pipeline
ner_pipeline = pipeline('ner')
results = ner_pipeline([1])

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

A'Apple is a company'

B['Apple', 'is', 'a', 'company']

C123

DNone

Attempts:

3 left

💡 Hint

Common Mistakes

Passing a list of words instead of a string.

Passing a number or None instead of text.

The NER pipeline expects a string input representing the sentence to analyze.

4fill in blank

hard

Fill both blanks to create a dictionary comprehension that maps words to their lengths only if the length is greater than 3.

NLP

{word: [1] for word in words if len(word) [2] 3}

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

Alen(word)

B<

C>

Dword

Attempts:

3 left

💡 Hint

Common Mistakes

Using the word itself as the value instead of its length.

Using '<' instead of '>' in the condition.

We want the dictionary to map each word to its length, but only include words longer than 3 characters.

5fill in blank

hard

Fill all three blanks to create a dictionary comprehension that maps uppercase words to their frequencies only if frequency is greater than 1.

NLP

{ [1]: [2] for [3], freq in word_freq.items() if freq > 1 }

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

Aword.upper()

Bfreq

Cword

Dfreq.upper()

Attempts:

3 left

💡 Hint

Common Mistakes

Using freq.upper() which is invalid since freq is a number.

Using 'freq' as the loop variable instead of 'word'.

The keys are uppercase words, values are frequencies, and the loop variable is 'word'.