Text preprocessing for RNNs in PyTorch - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is the purpose of text preprocessing before feeding data into an RNN?

Text preprocessing cleans and converts raw text into a numerical format that an RNN can understand and learn from. It helps improve model performance and training speed.

beginner

Why do we convert words into integers (tokenization) for RNN input?

RNNs work with numbers, not words. Tokenization assigns each unique word a number so the model can process sequences of numbers representing sentences.

beginner

What is padding in text preprocessing for RNNs?

Padding adds extra tokens (usually zeros) to make all input sequences the same length. This allows batch processing in RNNs without errors.

intermediate

How does PyTorch's `torch.nn.utils.rnn.pack_padded_sequence` help with variable-length sequences?

It lets the RNN ignore padded parts of sequences by packing only the real data, improving efficiency and preventing the model from learning from padding.

beginner

What role does a vocabulary dictionary play in text preprocessing for RNNs?

It maps each unique word to a unique integer index, enabling consistent tokenization and lookup during training and inference.

Why do we need to pad sequences before feeding them into an RNN?

A To increase the vocabulary size

B To make all sequences the same length for batch processing

C To convert words into integers

D To shuffle the data randomly

Padding ensures all sequences have the same length so they can be processed together in batches by the RNN.

What does tokenization do in text preprocessing?

A Converts text into numerical indices

B Removes stop words

C Normalizes text case

D Splits text into sentences

Tokenization assigns each word a unique number so the model can process text as numbers.

Which PyTorch function helps handle padded sequences efficiently in RNNs?

A torch.nn.CrossEntropyLoss

B torch.nn.functional.relu

C torch.optim.Adam

D torch.nn.utils.rnn.pack_padded_sequence

pack_padded_sequence allows the RNN to skip padded tokens during processing.

What is the main reason to build a vocabulary dictionary in text preprocessing?

A To map words to unique integers

B To remove punctuation

C To translate text to another language

D To generate random text

The vocabulary dictionary maps each unique word to an integer index for tokenization.

Which of these is NOT a typical step in text preprocessing for RNNs?

A Tokenization

B Padding

C Image resizing

D Building vocabulary

Image resizing is unrelated to text preprocessing.

Explain the key steps involved in preparing text data for training an RNN model.

Think about how raw text becomes numbers and how sequences are made uniform.

Describe how PyTorch helps handle variable-length text sequences when training RNNs.

Focus on PyTorch utilities that manage padded sequences.

Practice

1. Why do we split text into tokens before feeding it to an RNN?

easy

A. Because RNNs process sequences of numbers, not raw text

B. To reduce the size of the dataset

C. To make the text look nicer

D. Because tokens are easier to print

Solution

1. Step 1: Understand RNN input requirements

   RNNs work with sequences of numbers, not raw text strings.

2. Step 2: Role of tokenization

   Splitting text into tokens converts sentences into smaller units that can be mapped to numbers.

3. Final Answer:

   Because RNNs process sequences of numbers, not raw text -> Option A

4. Quick Check:

   Tokenization = Convert text to numbers [OK]

Hint: RNNs need numbers, so split text into tokens first [OK]

Common Mistakes:

• Thinking tokens are for making text prettier
• Believing tokenization reduces dataset size
• Confusing tokens with characters

2. Which PyTorch function is commonly used to pad sequences to the same length for batch processing?

easy

A. torch.nn.utils.rnn.pad_sequence

B. torch.tensor.pad

C. torch.pad_sequences

D. torch.nn.pad

Solution

1. Step 1: Identify PyTorch padding utilities

   PyTorch provides pad_sequence in torch.nn.utils.rnn to pad variable-length sequences.

2. Step 2: Check other options

   Functions like torch.tensor.pad or torch.nn.pad do not exist; torch.pad_sequences is not a PyTorch function.

3. Final Answer:

   torch.nn.utils.rnn.pad_sequence -> Option A

4. Quick Check:

   Use pad_sequence to pad RNN inputs [OK]

Hint: Remember: pad_sequence is in torch.nn.utils.rnn [OK]

Common Mistakes:

• Using non-existent torch.pad_sequences
• Confusing tensor.pad with pad_sequence
• Trying to pad manually without this function

3. Given the following code, what is the shape of the padded batch tensor?

import torch
from torch.nn.utils.rnn import pad_sequence

seq1 = torch.tensor([1, 2, 3])
seq2 = torch.tensor([4, 5])
seq3 = torch.tensor([6])
batch = pad_sequence([seq1, seq2, seq3], batch_first=True, padding_value=0)
print(batch.shape)

medium

A. (1, 3)

B. (3, 1)

C. (3, 3)

D. (3, 6)

Solution

1. Step 1: Understand input sequences

   Sequences have lengths 3, 2, and 1 respectively.

2. Step 2: pad_sequence with batch_first=true

   All sequences are padded to length 3 (max length), batch dimension is first, so shape is (3 sequences, 3 elements each).

3. Final Answer:

   (3, 3) -> Option C

4. Quick Check:

   Batch size = 3, max seq length = 3 [OK]

Hint: Batch shape = (number sequences, max sequence length) [OK]

Common Mistakes:

• Confusing batch_first=true with false
• Assuming padding adds length beyond max sequence
• Mixing up batch and sequence dimensions

4. What is wrong with this code snippet for preparing text sequences for an RNN?

import torch
from torch.nn.utils.rnn import pad_sequence

sentences = [[1, 2, 3, 4], [5, 6], [7]]
tensors = [torch.tensor(s) for s in sentences]
padded = pad_sequence(tensors)
print(padded.shape)

medium

A. torch.tensor cannot convert lists to tensors

B. pad_sequence is missing batch_first=true, so shape is unexpected

C. pad_sequence requires padding_value argument

D. The input lists must be numpy arrays, not lists

Solution

1. Step 1: Check pad_sequence default behavior

   By default, pad_sequence returns tensor with shape (max_seq_len, batch_size), not batch first.

2. Step 2: Effect on output shape

   Without batch_first=true, the printed shape will be (4, 3) instead of expected batch-first (3, 4) shape.

3. Final Answer:

   pad_sequence is missing batch_first=true, so shape is unexpected -> Option B

4. Quick Check:

   Use batch_first=true for (batch, seq_len) shape [OK]

Hint: Always add batch_first=true for batch as first dimension [OK]

Common Mistakes:

• Assuming pad_sequence pads automatically without batch_first
• Thinking torch.tensor can't convert lists
• Believing padding_value is mandatory

5. You have a batch of sentences tokenized as integer lists of different lengths. You want to feed them into an RNN in PyTorch. Which sequence of steps is correct for preprocessing?

hard

A. Tokenize text -> Pad sequences -> Convert tokens to integers -> Feed to RNN

B. Pad raw text strings -> Tokenize padded strings -> Convert tokens to integers -> Feed to RNN

C. Convert raw text to tensor -> Tokenize tensor -> Pad sequences -> Feed to RNN

D. Tokenize text -> Convert tokens to integers -> Pad sequences with pad_sequence(batch_first=true) -> Convert to tensor batch

Solution

1. Step 1: Tokenize text and convert tokens to integers

   First, split text into tokens, then map tokens to integers using a vocabulary.

2. Step 2: Pad sequences and prepare batch tensor

   Pad integer sequences to equal length using pad_sequence with batch_first=true, then feed the tensor batch to the RNN.

3. Final Answer:

   Tokenize text -> Convert tokens to integers -> Pad sequences with pad_sequence(batch_first=true) -> Convert to tensor batch -> Option D

4. Quick Check:

   Tokenize -> Integer map -> Pad -> Batch tensor [OK]

Hint: Tokenize first, then integer map, then pad sequences [OK]

Common Mistakes:

• Padding raw text instead of token integers
• Converting raw text directly to tensor
• Padding before converting tokens to integers