Text preprocessing for RNNs in PyTorch - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to tokenize the input sentence into words.

PyTorch

sentence = "I love machine learning"
tokens = sentence.[1]()

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

Asplit

Bjoin

Creplace

Dstrip

Attempts:

3 left

💡 Hint

Common Mistakes

Using join() instead of split() which combines words instead of splitting.

Using replace() which changes characters but does not split.

Using strip() which removes whitespace only at ends.

The split() method breaks the sentence into a list of words by spaces.

2fill in blank

medium

Complete the code to convert tokens to lowercase for uniformity.

PyTorch

tokens = ['I', 'Love', 'Machine', 'Learning']
lower_tokens = [word.[1]() for word in tokens]

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

Aupper

Blower

Ccapitalize

Dtitle

Attempts:

3 left

💡 Hint

Common Mistakes

Using upper() which converts to uppercase instead.

Using capitalize() which only changes the first letter.

Using title() which capitalizes each word.

The lower() method converts each word to lowercase, which helps the model treat words like 'Love' and 'love' the same.

3fill in blank

hard

Fix the error in the code to create a vocabulary dictionary mapping words to unique indices.

PyTorch

tokens = ['i', 'love', 'machine', 'learning', 'love']
vocab = {word: idx for idx, word in enumerate(set([1]))}

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

Alist

Bvocab

Ctokens

Drange

Attempts:

3 left

💡 Hint

Common Mistakes

Using vocab inside set() which is not defined yet.

Using list which is a type, not the variable.

Using range which is unrelated here.

We use set(tokens) to get unique words, then enumerate to assign each a unique index.

4fill in blank

hard

Fill both blanks to convert a list of tokens into a list of indices using the vocabulary.

PyTorch

tokens = ['i', 'love', 'machine']
indices = [[1][word] for [2] in tokens]

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

Avocab

Bword

Ctokens

Dindices

Attempts:

3 left

💡 Hint

Common Mistakes

Using tokens instead of vocab to get indices.

Using tokens as loop variable which is the list, not element.

Using indices as loop variable which is the output list.

We use the vocabulary dictionary vocab to get the index for each word in the tokens list.

5fill in blank

hard

Fill all three blanks to pad sequences to the same length using PyTorch.

PyTorch

import torch
from torch.nn.utils.rnn import [1]

sequences = [torch.tensor([1, 2, 3]), torch.tensor([4, 5])]
padded = [2](sequences, batch_first=True, padding_value=[3])

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

Apad_sequence

Bpad_packed_sequence

Cpack_sequence

D0

Attempts:

3 left

💡 Hint

Common Mistakes

Using pack_sequence which packs sequences but does not pad.

Using pad_packed_sequence which unpacks padded sequences.

Using pack_padded_sequence which packs padded sequences.

pad_sequence pads a list of variable-length tensors to the same length. We use padding_value=0 to pad with zeros.