Text preprocessing for RNNs in PyTorch - Model Pipeline Trace

Model Pipeline - Text preprocessing for RNNs

This pipeline shows how raw text data is cleaned and prepared step-by-step to be used as input for a Recurrent Neural Network (RNN). It converts sentences into numbers that the RNN can understand.

Data Flow - 7 Stages

1Raw Text Input

1000 sentences (variable length)→Collect raw sentences from dataset→1000 sentences (variable length)

"I love cats", "Deep learning is fun"

↓

2Lowercasing and Cleaning

1000 sentences (variable length)→Convert all letters to lowercase and remove punctuation→1000 sentences (variable length)

"i love cats", "deep learning is fun"

↓

3Tokenization

1000 sentences (variable length)→Split sentences into words (tokens)→1000 lists of tokens (variable length)

["i", "love", "cats"], ["deep", "learning", "is", "fun"]

↓

4Vocabulary Building

All tokens from 1000 sentences→Create a dictionary mapping each unique word to an integer index→Vocabulary size = 5000 words

{"i":1, "love":2, "cats":3, "deep":4, "learning":5, "is":6, "fun":7}

↓

5Numerical Encoding

1000 lists of tokens→Replace each token with its integer index from vocabulary→1000 lists of integers (variable length)

[1, 2, 3], [4, 5, 6, 7]

↓

6Padding

1000 lists of integers (variable length)→Add zeros to make all sequences the same length (max length = 6)→1000 lists of integers (length = 6)

[1, 2, 3, 0, 0, 0], [4, 5, 6, 7, 0, 0]

↓

7Tensor Conversion

1000 lists of integers (length = 6)→Convert lists into PyTorch tensors for model input→Tensor of shape (1000, 6)

tensor([[1, 2, 3, 0, 0, 0], [4, 5, 6, 7, 0, 0], ...])

Training Trace - Epoch by Epoch

Loss
1.2 |****
0.9 |***
0.7 |**
0.55|*
0.45| 
    +------------
     Epochs 1-5

Epoch	Loss ↓	Accuracy ↑	Observation
1	1.2	0.45	Model starts learning; loss is high and accuracy is low.
2	0.9	0.60	Loss decreases and accuracy improves as model learns patterns.
3	0.7	0.72	Continued improvement; model is fitting training data better.
4	0.55	0.80	Loss drops further; accuracy reaches a good level.
5	0.45	0.85	Model converges with low loss and high accuracy.

Prediction Trace - 4 Layers

Layer 1: Input Embedding Layer

Layer 2: RNN Layer

Layer 3: Fully Connected Layer

Layer 4: Softmax Activation

Model Quiz - 3 Questions

Why do we pad sequences to the same length before feeding them to the RNN?

A To increase the vocabulary size

B To remove stop words from sentences

C Because RNNs require inputs of equal length for batch processing

D To convert words into numbers

Key Insight

Text preprocessing transforms raw sentences into fixed-size numeric tensors that RNNs can process. Proper cleaning, tokenization, and padding are essential for effective learning and stable training.

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