Why different transformers serve different tasks in NLP - Test Your Understanding

Practice - 5 Tasks

1fill in blank

easy

Complete the code to load a transformer model for text classification.

NLP

from transformers import AutoModelForSequenceClassification
model = AutoModelForSequenceClassification.from_pretrained([1])

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

A"bert-base-uncased"

B"gpt2"

C"t5-small"

D"roberta-base"

Attempts:

3 left

💡 Hint

Common Mistakes

Choosing a model designed for text generation instead of classification.

The bert-base-uncased model is commonly used for sequence classification tasks.

2fill in blank

medium

Complete the code to tokenize input text for a transformer model.

NLP

from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained([1])
inputs = tokenizer("Hello world!", return_tensors="pt")

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

A"gpt2"

B"bert-base-uncased"

C"t5-small"

D"distilbert-base-uncased"

Attempts:

3 left

💡 Hint

Common Mistakes

Using a tokenizer that does not match the model architecture.

The tokenizer must match the model. Here, bert-base-uncased tokenizer is used.

3fill in blank

hard

Fix the error in the code to generate text using a transformer model.

NLP

from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained([1])
tokenizer = AutoTokenizer.from_pretrained("gpt2")
inputs = tokenizer("Hello, how are you?", return_tensors="pt")
outputs = model.generate(**inputs)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

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

A"gpt2"

B"roberta-base"

C"t5-small"

D"bert-base-uncased"

Attempts:

3 left

💡 Hint

Common Mistakes

Using a model designed for classification instead of generation.

The gpt2 model is a causal language model suitable for text generation.

4fill in blank

hard

Fill both blanks to create a transformer model and tokenizer for translation.

NLP

from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
model = AutoModelForSeq2SeqLM.from_pretrained([1])
tokenizer = AutoTokenizer.from_pretrained([2])
inputs = tokenizer("Translate this sentence.", return_tensors="pt")
outputs = model.generate(**inputs)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

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

A"t5-small"

B"bert-base-uncased"

D"gpt2"

Attempts:

3 left

💡 Hint

Common Mistakes

Mixing model and tokenizer names from different architectures.

The t5-small model and tokenizer are used for sequence-to-sequence tasks like translation.

5fill in blank

hard

Fill all three blanks to create a dictionary comprehension that filters tokens by length and converts them to uppercase.

NLP

tokens = ["hello", "to", "world", "a", "transformer"]
filtered = [1]: [2] for token in tokens if len(token) [3] 3

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

Atoken.upper()

Btoken

C>

D<

Attempts:

3 left

💡 Hint

Common Mistakes

Using the wrong comparison operator or swapping key and value.

This comprehension creates a dictionary with keys as uppercase tokens and values as original tokens, only for tokens longer than 3 characters.

Practice

1. Why do different transformer models exist for different NLP tasks?

easy

A. Because transformers do not use any training data

B. Because transformers are only designed for image processing

C. Because all transformers work exactly the same for every task

D. Because each task requires a special way to process and understand language

Solution

1. Step 1: Understand the role of transformers in NLP tasks

   Transformers are designed to handle language data, but different tasks like translation or classification need different ways to process inputs and outputs.

2. Step 2: Recognize why task-specific models exist

   Because tasks differ, models are fine-tuned or designed to best fit each task's needs, improving performance.

3. Final Answer:

   Because each task requires a special way to process and understand language -> Option D

4. Quick Check:

   Task needs shape model choice = A [OK]

Hint: Different tasks need different processing methods [OK]

Common Mistakes:

• Thinking all transformers are the same
• Believing transformers only work for images
• Ignoring the role of training data

2. Which of the following is the correct way to load a pretrained transformer model for text classification using the Hugging Face library?

easy

A. model = AutoTokenizer.from_pretrained('bert-base-uncased')

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

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

D. model = AutoModelForImageClassification.from_pretrained('bert-base-uncased')

Solution

1. Step 1: Identify the correct class for text classification

   For text classification, the correct class is AutoModelForSequenceClassification.

2. Step 2: Check the pretrained model name and method

   'bert-base-uncased' is a common pretrained model, and from_pretrained loads it properly.

3. Final Answer:

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

4. Quick Check:

   Text classification model loading = A [OK]

Hint: Use AutoModelForSequenceClassification for classification tasks [OK]

Common Mistakes:

• Using AutoModel instead of AutoModelForSequenceClassification
• Confusing tokenizer loading with model loading
• Using image classification model for text

3. Given this code snippet using a transformer for question answering, what will be the output type of outputs?

from transformers import AutoModelForQuestionAnswering, AutoTokenizer
model = AutoModelForQuestionAnswering.from_pretrained('distilbert-base-uncased-distilled-squad')
tokenizer = AutoTokenizer.from_pretrained('distilbert-base-uncased-distilled-squad')
inputs = tokenizer('Who is the president of the USA?', return_tensors='pt')
outputs = model(**inputs)

medium

A. A single number representing sentiment score

B. A tuple containing start and end logits for answer span

C. A sequence of translated text tokens

D. A classification label like 'positive' or 'negative'

Solution

1. Step 1: Identify the model type and task

   The model is AutoModelForQuestionAnswering, designed to find answer spans in text.

2. Step 2: Understand the output format for question answering models

   These models output start and end logits indicating where the answer begins and ends in the input.

3. Final Answer:

   A tuple containing start and end logits for answer span -> Option B

4. Quick Check:

   Question answering output = start/end logits = D [OK]

Hint: Question answering outputs start/end logits tuple [OK]

Common Mistakes:

• Expecting classification labels from QA models
• Confusing translation output with QA output
• Thinking output is a single sentiment score

4. You tried to use AutoModelForSeq2SeqLM for a text classification task but got wrong results. What is the likely error?

medium

A. Using a sequence-to-sequence model instead of a classification model

B. Not tokenizing the input text

C. Using the wrong optimizer

D. Loading the model without pretrained weights

Solution

1. Step 1: Understand model purpose

   AutoModelForSeq2SeqLM is for tasks like translation or summarization, not classification.

2. Step 2: Identify mismatch with task

   Using a seq2seq model for classification leads to wrong outputs because the model expects different input-output formats.

3. Final Answer:

   Using a sequence-to-sequence model instead of a classification model -> Option A

4. Quick Check:

   Model-task mismatch = seq2seq used for classification = C [OK]

Hint: Match model type to task type carefully [OK]

Common Mistakes:

• Ignoring model-task compatibility
• Forgetting to tokenize input
• Assuming optimizer causes output errors

5. You want to build a chatbot that answers questions based on a knowledge base. Which transformer model type should you choose and why?

hard

A. AutoModelForQuestionAnswering, because it finds answer spans in text

B. AutoModelForSequenceClassification, because it classifies sentiment

C. AutoModelForMaskedLM, because it predicts missing words

D. AutoModelForSeq2SeqLM, because it translates languages

Solution

1. Step 1: Understand chatbot task

   The chatbot needs to answer questions by finding relevant text spans in a knowledge base.

2. Step 2: Match model type to task

   AutoModelForQuestionAnswering is designed to locate answer spans, making it ideal for this chatbot.

3. Step 3: Exclude other options

   SequenceClassification is for sentiment, MaskedLM predicts missing words, Seq2SeqLM is for translation, so they don't fit the task.

4. Final Answer:

   AutoModelForQuestionAnswering, because it finds answer spans in text -> Option A

5. Quick Check:

   Chatbot answering needs QA model = B [OK]

Hint: Use QA models for answer span tasks like chatbots [OK]

Common Mistakes:

• Choosing classification or translation models incorrectly
• Confusing masked language models with QA models
• Not matching model to chatbot needs