BERT for text classification in PyTorch - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to load the BERT tokenizer.

PyTorch

from transformers import [1]
tokenizer = [1].from_pretrained('bert-base-uncased')

Drag options to blanks, or click blank then click option'

ABertTokenizer

BBertModel

CAutoTokenizer

DAutoModel

Attempts:

3 left

💡 Hint

Common Mistakes

Using BertModel instead of a tokenizer.

Using BertTokenizer which is correct but less flexible than AutoTokenizer.

The AutoTokenizer class loads the correct tokenizer for BERT automatically.

2fill in blank

medium

Complete the code to tokenize input text for BERT.

PyTorch

inputs = tokenizer('[1]', return_tensors='pt', padding=True, truncation=True)

Drag options to blanks, or click blank then click option'

ABERT is great for NLP.

BHello, how are you?

CI love machine learning.

DThis is a test sentence.

Attempts:

3 left

💡 Hint

Common Mistakes

Not passing a string to the tokenizer.

Passing a list instead of a string.

Any sentence can be tokenized, but here we want to fill the blank with a sample sentence. 'This is a test sentence.' is a clear example.

3fill in blank

hard

Fix the error in the code to get BERT's pooled output for classification.

PyTorch

outputs = model(**inputs)
pooled_output = outputs.[1]

Drag options to blanks, or click blank then click option'

Apooler_output

Blast_hidden_state

Chidden_states

Dlogits

Attempts:

3 left

💡 Hint

Common Mistakes

Using last_hidden_state which is the sequence output, not pooled.

Trying to access logits directly from model output without a classification head.

The pooler_output is the pooled representation of the [CLS] token used for classification.

4fill in blank

hard

Fill both blanks to define a simple classifier head on top of BERT's pooled output.

PyTorch

import torch.nn as nn

class BertClassifier(nn.Module):
    def __init__(self, bert_model):
        super().__init__()
        self.bert = bert_model
        self.classifier = nn.[1](bert_model.config.hidden_size, [2])

    def forward(self, input_ids, attention_mask):
        outputs = self.bert(input_ids=input_ids, attention_mask=attention_mask)
        pooled_output = outputs.pooler_output
        return self.classifier(pooled_output)

Drag options to blanks, or click blank then click option'

ALinear

BReLU

C2

DDropout

Attempts:

3 left

💡 Hint

Common Mistakes

Using activation functions like ReLU or Dropout as the classifier layer.

Setting the output size incorrectly.

The classifier is a Linear layer mapping from BERT's hidden size to the number of classes, here 2.

5fill in blank

hard

Fill all three blanks to compute the accuracy metric after predictions.

PyTorch

import torch

preds = torch.argmax(logits, dim=[1])
correct = (preds == labels).sum().item()
accuracy = correct / [2]
print(f'Accuracy: {accuracy:.2f}')

# Assuming labels is a tensor of size [3]

Drag options to blanks, or click blank then click option'

A1

B0

Clen(labels)

Dlabels.size(0)

Attempts:

3 left

💡 Hint

Common Mistakes

Using wrong dimension in argmax.

Dividing by len(labels) which is not a tensor method.

Using incorrect batch size calculation.

We take argmax over dimension 1 to get the predicted class for each sample in the batch, then divide correct count by batch size using labels.size(0).

Practice

1. What is the main advantage of using BERT for text classification compared to traditional bag-of-words models?

easy

A. BERT understands the context of words in a sentence.

B. BERT uses fewer parameters than bag-of-words models.

C. BERT requires no preprocessing of text data.

D. BERT only works with short texts.

Solution

1. Step 1: Understand BERT's design

   BERT reads words in context, meaning it looks at surrounding words to understand meaning better.

2. Step 2: Compare with bag-of-words

   Bag-of-words treats words independently, ignoring order and context, which limits understanding.

3. Final Answer:

   BERT understands the context of words in a sentence. -> Option A

4. Quick Check:

   Contextual understanding = A [OK]

Hint: Remember BERT reads words with context, unlike bag-of-words [OK]

Common Mistakes:

• Thinking BERT uses fewer parameters
• Assuming BERT needs no preprocessing
• Believing BERT only works on short texts

2. Which of the following is the correct way to load a pretrained BERT model for sequence classification in PyTorch?

easy

A. model = torch.load('bert-base-uncased')

B. model = BertTokenizer.from_pretrained('bert-base-uncased')

C. model = BertForSequenceClassification.from_pretrained('bert-base-uncased')

D. model = nn.Sequential('bert-base-uncased')

Solution

1. Step 1: Identify correct class for model loading

   BertForSequenceClassification is the class to load pretrained BERT models for classification tasks.

2. Step 2: Check method usage

   from_pretrained is the method to load pretrained weights by model name.

3. Final Answer:

   model = BertForSequenceClassification.from_pretrained('bert-base-uncased') -> Option C

4. Quick Check:

   Use BertForSequenceClassification.from_pretrained = A [OK]

Hint: Use from_pretrained with BertForSequenceClassification for classification models [OK]

Common Mistakes:

• Using BertTokenizer to load model weights
• Trying to load model with torch.load without saving first
• Using nn.Sequential incorrectly for BERT

3. Given the following code snippet, what will be the shape of the logits output?

from transformers import BertTokenizer, BertForSequenceClassification
import torch

tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
model = BertForSequenceClassification.from_pretrained('bert-base-uncased', num_labels=3)

inputs = tokenizer(['Hello world!', 'BERT is great.'], padding=True, return_tensors='pt')
outputs = model(**inputs)
logits = outputs.logits
print(logits.shape)

medium

A. torch.Size([3, 2])

B. torch.Size([2, 3])

C. torch.Size([2, 768])

D. torch.Size([1, 3])

Solution

1. Step 1: Understand batch size and labels

   Input has 2 sentences, so batch size is 2. num_labels=3 means 3 classes.

2. Step 2: Check output logits shape

   Logits shape is (batch_size, num_labels), so (2, 3).

3. Final Answer:

   torch.Size([2, 3]) -> Option B

4. Quick Check:

   Batch size 2 and 3 labels = (2, 3) [OK]

Hint: Logits shape = (batch size, number of classes) [OK]

Common Mistakes:

• Confusing batch size and label dimension order
• Assuming output shape matches hidden size (768)
• Ignoring batch size in output shape

4. You run this code but get an error: TypeError: forward() got an unexpected keyword argument 'input_ids'. What is the likely cause?

outputs = model(input_ids=inputs['input_ids'], attention_mask=inputs['attention_mask'])

medium

A. The model variable is a BertTokenizer, not BertForSequenceClassification.

B. The inputs dictionary is missing 'input_ids' key.

C. The model was not loaded with from_pretrained.

D. The attention_mask argument is not supported by BERT models.

Solution

1. Step 1: Analyze error message

   The error says forward() got unexpected keyword 'input_ids', meaning the model does not accept this argument.

2. Step 2: Identify model type mismatch

   BertTokenizer does not have a forward method and does not accept input_ids; only BertForSequenceClassification does.

3. Final Answer:

   The model variable is a BertTokenizer, not BertForSequenceClassification. -> Option A

4. Quick Check:

   Wrong model type causes unexpected argument error = D [OK]

Hint: Check if model is BertForSequenceClassification, not tokenizer [OK]

Common Mistakes:

• Confusing tokenizer with model
• Assuming attention_mask is unsupported
• Thinking inputs dictionary is missing keys

5. You want to fine-tune BERT for a 4-class text classification task with imbalanced classes. Which approach helps improve model performance?

hard

A. Set num_labels=2 since 4 classes is too many for BERT.

B. Remove the attention_mask to speed up training.

C. Freeze all BERT layers and train only the final classifier layer.

D. Use weighted loss function to give more importance to minority classes.

Solution

1. Step 1: Understand class imbalance problem

   Imbalanced classes cause the model to favor majority classes, hurting minority class accuracy.

2. Step 2: Choose appropriate solution

   Weighted loss assigns higher penalty to errors on minority classes, helping balance learning.

3. Final Answer:

   Use weighted loss function to give more importance to minority classes. -> Option D

4. Quick Check:

   Weighted loss helps with imbalance = C [OK]

Hint: Apply weighted loss to handle class imbalance [OK]

Common Mistakes:

• Removing attention_mask harms input understanding
• Reducing num_labels loses class info
• Freezing all layers limits fine-tuning benefits