Sequence-to-sequence architecture in NLP

Introduction

Sequence-to-sequence architecture helps computers turn one sequence of information into another. It is useful when the input and output are both sequences, like translating languages or summarizing text.

Translating a sentence from English to French.

Turning a spoken sentence into written text.

Summarizing a long article into a short paragraph.

Generating a reply in a chatbot conversation.

Converting a sequence of numbers into another sequence, like time series prediction.

Syntax

NLP

encoder = Encoder(input_size, hidden_size)
decoder = Decoder(hidden_size, output_size)

# Forward pass
encoder_outputs, encoder_hidden = encoder(input_sequence)
output_sequence = decoder(encoder_hidden, target_length)

The encoder reads the input sequence and creates a summary called the hidden state.

The decoder uses this hidden state to generate the output sequence step by step.

Examples

This example shows creating an encoder and decoder with specific sizes, then running them on input to get output.

NLP

encoder = Encoder(10, 20)
decoder = Decoder(20, 15)

encoder_outputs, encoder_hidden = encoder(input_seq)
output_seq = decoder(encoder_hidden, 5)

Here, both encoder and decoder use simple RNN layers to process sequences.

NLP

# Using a simple RNN encoder and decoder
encoder = SimpleRNNEncoder(input_dim=50, hidden_dim=100)
decoder = SimpleRNNDecoder(hidden_dim=100, output_dim=50)

enc_out, enc_hidden = encoder(input_seq)
predicted_seq = decoder(enc_hidden, max_length=10)

Sample Model

This code builds a simple sequence-to-sequence model using PyTorch. The encoder reads the input sequence and creates a hidden state. The decoder uses this hidden state to generate a new sequence of length 4. The output shape and a sample output vector are printed.

NLP

import torch
import torch.nn as nn

class Encoder(nn.Module):
    def __init__(self, input_size, hidden_size):
        super().__init__()
        self.rnn = nn.GRU(input_size, hidden_size, batch_first=True)
    def forward(self, x):
        outputs, hidden = self.rnn(x)
        return outputs, hidden

class Decoder(nn.Module):
    def __init__(self, hidden_size, output_size):
        super().__init__()
        self.rnn = nn.GRU(output_size, hidden_size, batch_first=True)
        self.fc = nn.Linear(hidden_size, output_size)
    def forward(self, hidden, seq_len):
        batch_size = hidden.size(1)
        inputs = torch.zeros(batch_size, 1, self.fc.out_features)
        outputs = []
        for _ in range(seq_len):
            out, hidden = self.rnn(inputs, hidden)
            out = self.fc(out)
            outputs.append(out)
            inputs = out
        return torch.cat(outputs, dim=1)

# Create dummy input: batch=2, seq_len=3, input_size=4
input_seq = torch.randn(2, 3, 4)

encoder = Encoder(input_size=4, hidden_size=5)
decoder = Decoder(hidden_size=5, output_size=6)

encoder_outputs, encoder_hidden = encoder(input_seq)
output_seq = decoder(encoder_hidden, seq_len=4)

print('Output shape:', output_seq.shape)
print('Output sample:', output_seq[0, 0].detach().numpy())

Important Notes

The encoder summarizes the input sequence into a fixed-size hidden state.

The decoder generates the output sequence one step at a time, often using its previous output as the next input.

Sequence lengths can vary, so models often use padding or special tokens to handle this.

Summary

Sequence-to-sequence models turn one sequence into another, like translating or summarizing.

They use an encoder to read input and a decoder to write output.

This architecture is key for many language and time-based tasks.

Practice

1. What is the main role of the encoder in a sequence-to-sequence model?

easy

A. To generate the output sequence directly

B. To read and understand the input sequence

C. To evaluate the model's accuracy

D. To preprocess the data before training

Solution

1. Step 1: Understand the encoder's function

   The encoder processes the input sequence and converts it into a meaningful representation.

2. Step 2: Differentiate encoder from decoder

   The decoder uses this representation to generate the output sequence, so it does not directly read input.

3. Final Answer:

   To read and understand the input sequence -> Option B

4. Quick Check:

   Encoder = input reader [OK]

Hint: Encoder reads input; decoder writes output [OK]

Common Mistakes:

• Confusing encoder with decoder
• Thinking encoder generates output
• Assuming encoder evaluates accuracy

2. Which of the following is the correct way to describe the decoder in a sequence-to-sequence model?

easy

A. It generates the output sequence from the encoded input

B. It encodes the input sequence into a fixed vector

C. It normalizes the input data before encoding

D. It splits the input sequence into smaller parts

Solution

1. Step 1: Identify decoder's role

   The decoder takes the encoded input and produces the output sequence step-by-step.

2. Step 2: Eliminate incorrect options

   Encoding is done by the encoder, not the decoder; normalization and splitting are preprocessing steps.

3. Final Answer:

   It generates the output sequence from the encoded input -> Option A

4. Quick Check:

   Decoder = output generator [OK]

Hint: Decoder creates output from encoder's info [OK]

Common Mistakes:

• Mixing encoder and decoder roles
• Confusing preprocessing with decoding
• Assuming decoder encodes input

3. Consider this simplified pseudocode for a sequence-to-sequence model:

encoded = encoder(input_sequence)
output = decoder(encoded)
print(len(output))

If the input sequence length is 5 and the model is trained to translate to a sequence of length 7, what will len(output) print?

medium

A. 5

B. Cannot determine without more info

C. 12

D. 7

Solution

1. Step 1: Understand input and output lengths

   The input sequence length is 5, but the model is trained to produce output sequences of length 7.

2. Step 2: Recognize decoder output length

   The decoder generates output sequences based on training, so output length should be 7 regardless of input length.

3. Final Answer:

   7 -> Option D

4. Quick Check:

   Output length = trained target length = 7 [OK]

Hint: Output length matches target, not input length [OK]

Common Mistakes:

• Assuming output length equals input length
• Adding input and output lengths
• Saying output length is unknown

4. You have this code snippet for a sequence-to-sequence model training step:

for input_seq, target_seq in dataset:
    encoded = encoder(input_seq)
    output = decoder(encoded)
    loss = loss_function(output, target_seq)
    loss.backward()
    optimizer.step()
    optimizer.zero_grad()

What is the likely error in this code?

medium

A. optimizer.zero_grad() should be called before loss.backward()

B. optimizer.step() should be called before loss.backward()

C. Missing call to optimizer.zero_grad() before loss.backward()

D. optimizer.zero_grad() should be called before optimizer.step()

Solution

1. Step 1: Recall training step order

   Gradients must be cleared before computing new gradients with loss.backward().

2. Step 2: Identify correct zero_grad() placement

   optimizer.zero_grad() should be called before loss.backward(), not after optimizer.step().

3. Final Answer:

   Missing call to optimizer.zero_grad() before loss.backward() -> Option C

4. Quick Check:

   Clear grads before backward pass [OK]

Hint: Call zero_grad() before backward() [OK]

Common Mistakes:

• Calling zero_grad() after backward()
• Calling optimizer.step() before backward()
• Skipping zero_grad() entirely

5. In a sequence-to-sequence model for language translation, why might adding an attention mechanism improve performance?

hard

A. It allows the decoder to focus on relevant parts of the input sequence dynamically

B. It reduces the size of the input sequence to a fixed vector

C. It speeds up training by skipping the encoder step

D. It replaces the decoder with a simpler model

Solution

1. Step 1: Understand attention's purpose

   Attention helps the decoder look at different parts of the input sequence when generating each output token.

2. Step 2: Compare with fixed vector encoding

   Without attention, the encoder compresses input into one fixed vector, which can lose details.

3. Step 3: Eliminate incorrect options

   Attention does not reduce input size, skip encoder, or replace decoder; it enhances focus during decoding.

4. Final Answer:

   It allows the decoder to focus on relevant parts of the input sequence dynamically -> Option A

5. Quick Check:

   Attention = dynamic focus on input [OK]

Hint: Attention helps decoder focus on input parts [OK]

Common Mistakes:

• Thinking attention reduces input size
• Believing attention skips encoder
• Assuming attention replaces decoder