Answer span extraction in NLP - Practice Problems & Coding Challenges

Challenge - 5 Problems

🧠 Conceptual

intermediate

What is the main goal of answer span extraction in NLP?

In simple terms, what does answer span extraction try to do when given a question and a paragraph?

A Find the exact part of the paragraph that answers the question

B Generate a new answer unrelated to the paragraph

C Summarize the entire paragraph without focusing on the question

D Translate the paragraph into another language

💡 Hint

Think about pointing to a specific piece of text that answers the question.

Answer span extraction means locating the exact text segment in the paragraph that answers the question, not creating new text or unrelated tasks.

❓ Predict Output

intermediate

What is the output of this answer span extraction code snippet?

Given the paragraph and question, what answer span does the model predict?

NLP

paragraph = 'The Eiffel Tower is located in Paris and is one of the most famous landmarks.'
question = 'Where is the Eiffel Tower located?'

# Simulated model output (start and end indices)
start_index = 5
end_index = 6

answer_tokens = paragraph.split()[start_index:end_index+1]
answer = ' '.join(answer_tokens)
print(answer)

A in Paris

B located in Paris

C Paris and is

D The Eiffel Tower

💡 Hint

Look at the words between indices 5 and 6 in the paragraph split by spaces.

The paragraph split by spaces is ['The', 'Eiffel', 'Tower', 'is', 'located', 'in', 'Paris', ...]. Indices 5 and 6 correspond to 'in' and 'Paris', so the answer is 'in Paris'. But the code prints from index 5 to 6 inclusive, so 'located in Paris' is from indices 4 to 6. Since start_index=5, end_index=6, the answer is 'in Paris'. So option A is correct.

❓ Model Choice

advanced

Which model architecture is best suited for answer span extraction tasks?

Choose the model type that is designed to predict start and end positions of answers in a paragraph.

A Sequence-to-sequence model generating answers word by word

B Transformer-based model with token classification heads for start and end positions

C Unsupervised clustering model grouping similar sentences

D Generative adversarial network creating new paragraphs

💡 Hint

Think about models that output positions rather than generating text.

Answer span extraction models typically use transformers with two output heads predicting start and end token positions in the input text.

❓ Metrics

advanced

Which metric best evaluates answer span extraction accuracy?

When checking if the predicted answer span matches the true answer span, which metric is most appropriate?

A BLEU score measuring n-gram overlap

B Mean Squared Error between token embeddings

C Exact Match (EM) score checking exact span equality

D Perplexity measuring language model uncertainty

💡 Hint

Think about a metric that checks if the predicted answer is exactly the same as the true answer.

Exact Match (EM) score is used to check if the predicted answer span exactly matches the ground truth span, which is crucial for span extraction tasks.

🔧 Debug

expert

Why does this answer span extraction code produce an empty answer?

Consider this code snippet that tries to extract an answer span but returns an empty string. What is the most likely cause?

NLP

paragraph = 'Machine learning helps computers learn from data.'
start_index = 7
end_index = 5

answer_tokens = paragraph.split()[start_index:end_index+1]
answer = ' '.join(answer_tokens)
print(answer)

A The split method is called incorrectly without parentheses

B The paragraph string is empty, so no tokens exist

C The join method is used on a string instead of a list

D start_index is greater than end_index, so the slice is empty

💡 Hint

Check the order of start and end indices in the slice.

In Python, slicing with a start index greater than the end index returns an empty list, so no tokens are joined and the answer is empty.