Text preprocessing for RNNs in PyTorch

Introduction

Text preprocessing helps turn words into numbers so RNNs can understand and learn from text.

When you want to teach a computer to understand sentences.

When building chatbots that reply to messages.

When analyzing customer reviews to find feelings.

When translating languages using a neural network.

When predicting the next word in a sentence.

Syntax

PyTorch

import torch
from torchtext.vocab import build_vocab_from_iterator
from torch.nn.utils.rnn import pad_sequence

def tokenize(text):
    return text.lower().split()

# Build vocabulary from tokenized texts
vocab = build_vocab_from_iterator(tokenize(text) for text in dataset, specials=["<pad>"])

# Convert text to list of token ids
def text_to_ids(text):
    return [vocab[token] for token in tokenize(text)]

# Pad sequences to same length
padded_batch = pad_sequence([torch.tensor(text_to_ids(t)) for t in batch], batch_first=True)

Tokenization splits text into words or pieces.

Padding makes all sequences the same length for batch processing.

Examples

Splits the sentence into words: ['hello', 'world']

PyTorch

text = "Hello world"
tokens = tokenize(text)
print(tokens)

Converts words to numbers using the vocabulary.

PyTorch

ids = text_to_ids("Hello world")
print(ids)

Pads shorter sequences with zeros to match the longest.

PyTorch

batch = ["Hello world", "Hi"]
padded = pad_sequence([torch.tensor(text_to_ids(t)) for t in batch], batch_first=True)
print(padded)

Sample Model

This code shows how to turn sentences into numbers and pad them so RNNs can process batches.

PyTorch

import torch
from torchtext.vocab import build_vocab_from_iterator
from torch.nn.utils.rnn import pad_sequence

def tokenize(text):
    return text.lower().split()

# Sample dataset
dataset = ["I love machine learning", "Deep learning is fun", "RNNs handle sequences"]

# Build vocabulary
vocab = build_vocab_from_iterator(tokenize(text) for text in dataset, specials=["<pad>"])

# Convert text to token ids

def text_to_ids(text):
    return [vocab[token] for token in tokenize(text)]

# Prepare batch
batch = ["I love machine learning", "RNNs handle sequences"]
token_ids = [torch.tensor(text_to_ids(text)) for text in batch]

# Pad sequences
padded_batch = pad_sequence(token_ids, batch_first=True, padding_value=vocab['<pad>'])

print("Vocabulary tokens:", vocab.get_itos())
print("Token IDs for batch:", token_ids)
print("Padded batch tensor:", padded_batch)

Important Notes

Always lowercase text to reduce vocabulary size.

Padding uses zeros by default; make sure your model ignores padding tokens.

Vocabulary maps words to unique numbers for the model.

Summary

Text must be split into tokens before feeding to RNNs.

Tokens are converted to numbers using a vocabulary.

Sequences are padded to the same length for batch processing.

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