GRU for text in NLP - Cheat Sheet & Quick Revision

Recall & Review

beginner

What does GRU stand for in machine learning?

GRU stands for Gated Recurrent Unit, a type of neural network layer used to process sequences like text.

beginner

How does a GRU help in understanding text sequences?

A GRU keeps track of important information from earlier words and decides what to remember or forget, helping the model understand context in text.

intermediate

Name the two main gates in a GRU cell and their roles.

The two main gates are the update gate, which decides how much past information to keep, and the reset gate, which decides how to combine new input with past memory.

intermediate

Why might GRUs be preferred over LSTMs for some text tasks?

GRUs are simpler with fewer parameters, making them faster to train and sometimes better for smaller datasets while still capturing sequence information well.

beginner

In a text classification task using a GRU, what is the typical output after the GRU layer?

The typical output is a fixed-size vector summarizing the text, which is then passed to a classifier like a dense layer to predict categories.

What is the main purpose of the update gate in a GRU?

A To generate the final output directly

B To decide how much past information to keep

C To reset the entire memory

D To increase the learning rate

The update gate controls how much of the past information is kept for the current step.

Which of these is a benefit of using GRUs over traditional RNNs for text?

A They can remember longer sequences better

B They require no training

C They always produce shorter outputs

D They do not use gates

GRUs use gates to better remember important information over longer sequences compared to basic RNNs.

In text processing, what kind of data does a GRU layer take as input?

A Sequences of word or character vectors

B Single numbers only

C Images

D Audio files

GRUs process sequences, so they take sequences of vectors representing words or characters as input.

What does the reset gate in a GRU do?

A Removes all past information

B Decides the learning rate

C Outputs the final prediction

D Controls how to combine new input with past memory

The reset gate decides how much past memory to forget when combining with new input.

Which task is a GRU commonly used for in NLP?

A Image recognition

B Sorting numbers

C Text classification

D Database queries

GRUs are often used for tasks like text classification where understanding sequences is important.

Explain how a GRU processes a sequence of words in a text.

Think about how the GRU decides what to remember and what to forget at each word.

Describe the advantages of using a GRU over a simple RNN for text tasks.

Focus on how GRUs improve remembering important information in text.

Practice

1. What is the main advantage of using a GRU (Gated Recurrent Unit) in text processing tasks?

easy

A. It helps the model remember important information over time while ignoring less important details.

B. It increases the size of the input text automatically.

C. It converts text into images for better analysis.

D. It removes all punctuation from the text before processing.

Solution

1. Step 1: Understand GRU's role in memory

   GRU units are designed to keep important information from previous steps and forget irrelevant data, helping with sequence tasks like text.

2. Step 2: Compare options to GRU function

   Only It helps the model remember important information over time while ignoring less important details. correctly describes this memory feature; others describe unrelated or incorrect functions.

3. Final Answer:

   It helps the model remember important information over time while ignoring less important details. -> Option A

4. Quick Check:

   GRU memory feature = A [OK]

Hint: GRU remembers key info, forgets noise in sequences [OK]

Common Mistakes:

• Thinking GRU changes input size
• Confusing GRU with data preprocessing
• Assuming GRU outputs images

2. Which of the following is the correct way to define a GRU layer in Python using PyTorch for text input with embedding size 100 and hidden size 50?

easy

A. nn.GRU(hidden_size=100, input_size=50)

B. nn.GRU(50, 100)

C. nn.GRU(input_size=100, hidden_size=50)

D. nn.GRU(100)

Solution

1. Step 1: Recall PyTorch GRU parameters

   PyTorch GRU expects input_size first (embedding size), then hidden_size (number of features in hidden state).

2. Step 2: Match parameters to given sizes

   Embedding size is 100, hidden size is 50, so nn.GRU(input_size=100, hidden_size=50) is correct.

3. Final Answer:

   nn.GRU(input_size=100, hidden_size=50) -> Option C

4. Quick Check:

   input_size=100, hidden_size=50 = B [OK]

Hint: Input size first, hidden size second in nn.GRU() [OK]

Common Mistakes:

• Swapping input_size and hidden_size
• Using positional args incorrectly
• Omitting required parameters

3. Given the following PyTorch code snippet, what will be the shape of the output tensor after passing input through the GRU?

import torch
import torch.nn as nn

gru = nn.GRU(input_size=10, hidden_size=20, batch_first=True)
input = torch.randn(5, 7, 10)  # batch=5, seq_len=7, input_size=10
output, hidden = gru(input)
print(output.shape)

medium

A. (7, 5, 20)

B. (5, 7, 20)

C. (5, 20, 7)

D. (5, 7, 10)

Solution

1. Step 1: Understand GRU output shape with batch_first=true

   Output shape is (batch_size, sequence_length, hidden_size) when batch_first=true.

2. Step 2: Match given input sizes

   Input batch=5, seq_len=7, hidden_size=20, so output shape is (5, 7, 20).

3. Final Answer:

   (5, 7, 20) -> Option B

4. Quick Check:

   Output shape = (batch, seq_len, hidden_size) = A [OK]

Hint: With batch_first=true, output shape is (batch, seq_len, hidden) [OK]

Common Mistakes:

• Confusing batch and sequence dimensions
• Ignoring batch_first=true effect
• Assuming output shape equals input shape

4. You wrote this code to create a GRU for text classification but get a runtime error:

gru = nn.GRU(input_size=50, hidden_size=100)
input = torch.randn(32, 10, 100)  # batch=32, seq_len=10, input_size=100
output, hidden = gru(input)

What is the likely cause of the error?

medium

A. Input size 100 does not match GRU input_size 50

B. Batch size 32 is too large for GRU

C. Sequence length 10 is invalid for GRU

D. GRU requires input to be 2D tensor, not 3D

Solution

1. Step 1: Check GRU input_size vs input tensor last dimension

   GRU expects input_size=50, but input tensor last dimension is 100, causing mismatch.

2. Step 2: Understand tensor shape requirements

   GRU input shape should be (batch, seq_len, input_size). Here input_size dimension must match GRU's input_size parameter.

3. Final Answer:

   Input size 100 does not match GRU input_size 50 -> Option A

4. Quick Check:

   Input size mismatch = C [OK]

Hint: Match input tensor last dim to GRU input_size [OK]

Common Mistakes:

• Blaming batch size for error
• Thinking sequence length is invalid
• Assuming GRU only accepts 2D input

5. You want to build a GRU-based model to classify movie reviews as positive or negative. Your dataset has variable-length reviews. Which approach best handles variable-length sequences with a GRU in PyTorch?

hard

A. Convert text to images and use CNN instead of GRU.

B. Truncate all sequences to length 1 and feed to GRU.

C. Feed raw sequences directly without padding or packing.

D. Pad all sequences to the same length and use pack_padded_sequence before GRU.

Solution

1. Step 1: Understand variable-length sequence handling

   GRU requires fixed-length inputs or packed sequences to handle variable lengths efficiently.

2. Step 2: Use padding and packing for variable-length inputs

   Padding sequences to max length and using pack_padded_sequence lets GRU ignore padded parts during processing.

3. Final Answer:

   Pad all sequences to the same length and use pack_padded_sequence before GRU. -> Option D

4. Quick Check:

   Padding + pack_padded_sequence = D [OK]

Hint: Pad sequences and pack before GRU for variable lengths [OK]

Common Mistakes:

• Truncating sequences too short loses info
• Feeding raw variable-length sequences causes errors
• Switching to CNN ignores GRU benefits