Extractive QA concept in NLP

Introduction

Extractive Question Answering (QA) helps find exact answers from a given text. It picks the right part of the text as the answer.

You want to find a specific fact from a document, like a date or name.

You have a paragraph and want to answer questions about it quickly.

You want a system to help users get quick answers from manuals or FAQs.

You need to build a chatbot that answers questions using a fixed text source.

You want to highlight the exact sentence or phrase that answers a question.

Syntax

NLP

model = ExtractiveQAModel()
answer = model.answer(question, context)

The question is what you want to know.

The context is the text where the answer is found.

Examples

The model finds "Paris, France" as the answer.

NLP

question = "Where is the Eiffel Tower located?"
context = "The Eiffel Tower is in Paris, France."
answer = model.answer(question, context)

The model extracts "Jane Austen" as the answer.

NLP

question = "Who wrote 'Pride and Prejudice'?"
context = "Jane Austen wrote 'Pride and Prejudice' in 1813."
answer = model.answer(question, context)

Sample Model

This code uses a ready-made model to find the answer in the context. It prints the answer and how confident the model is.

NLP

from transformers import pipeline

# Load a pre-trained extractive QA pipeline
qa_pipeline = pipeline('question-answering')

context = "The Statue of Liberty is located in New York Harbor. It was a gift from France."
question = "Where is the Statue of Liberty located?"

result = qa_pipeline(question=question, context=context)

print(f"Answer: {result['answer']}")
print(f"Score: {result['score']:.2f}")

Important Notes

Extractive QA only picks answers from the given text; it does not generate new information.

Good context quality helps the model find better answers.

Models may give a confidence score showing how sure they are about the answer.

Summary

Extractive QA finds exact answers inside a text.

It works by selecting a part of the context that answers the question.

It is useful for quick fact-finding from documents or chats.

Practice

1. What is the main goal of extractive question answering (QA)?

easy

A. To translate the question into another language

B. To generate a new answer not present in the text

C. To summarize the entire text into a short paragraph

D. To find the exact answer span within a given text

Solution

1. Step 1: Understand extractive QA purpose

   Extractive QA aims to locate the exact part of the text that answers the question.

2. Step 2: Compare options with definition

   Only To find the exact answer span within a given text describes finding the exact answer span inside the text, which matches extractive QA.

3. Final Answer:

   To find the exact answer span within a given text -> Option D

4. Quick Check:

   Extractive QA = find exact answer span [OK]

Hint: Extractive QA picks text parts, not creates new answers [OK]

Common Mistakes:

• Confusing extractive QA with generative QA
• Thinking extractive QA summarizes text
• Assuming extractive QA translates questions

2. Which of the following is the correct way to represent an extractive QA model's output?

easy

A. Span of text indices indicating the answer start and end

B. Single integer representing the answer length

C. List of unrelated keywords from the text

D. Boolean value indicating if the answer exists

Solution

1. Step 1: Recall extractive QA output format

   Extractive QA models output the start and end positions of the answer span in the text.

2. Step 2: Match options to output format

   Only Span of text indices indicating the answer start and end correctly describes output as text span indices.

3. Final Answer:

   Span of text indices indicating the answer start and end -> Option A

4. Quick Check:

   Output = start and end indices [OK]

Hint: Extractive QA outputs answer span positions, not just length [OK]

Common Mistakes:

• Choosing answer length instead of span indices
• Confusing keywords with answer span
• Thinking output is just true/false

3. Given the context: 'The Eiffel Tower is located in Paris.' and the question: 'Where is the Eiffel Tower?', what would an extractive QA model most likely output?

medium

A. "Eiffel Tower"

B. "located"

C. "Paris"

D. "The Eiffel Tower is located"

Solution

1. Step 1: Understand question and context

   The question asks for the location of the Eiffel Tower, which is stated as "Paris" in the context.

2. Step 2: Identify exact answer span

   The extractive QA model selects the exact text span answering the question, which is "Paris".

3. Final Answer:

   "Paris" -> Option C

4. Quick Check:

   Answer = "Paris" [OK]

Hint: Extractive QA picks exact answer phrase from context [OK]

Common Mistakes:

• Selecting part of the question as answer
• Choosing unrelated words from context
• Picking longer phrases than needed

4. Consider this extractive QA model output code snippet:

start_idx = 10
end_idx = 5
answer = context[start_idx:end_idx]

What is the main issue here?

medium

A. The end index is smaller than the start index, causing an empty answer

B. The indices are correct and will extract the answer properly

C. The code is missing a question input

D. The context variable is undefined

Solution

1. Step 1: Analyze index values

   The start index is 10 and the end index is 5, which is smaller than start.

2. Step 2: Understand slicing behavior

   In Python, slicing with start > end returns an empty string, so no answer is extracted.

3. Final Answer:

   The end index is smaller than the start index, causing an empty answer -> Option A

4. Quick Check:

   End index < start index = empty slice [OK]

Hint: End index must be >= start index for valid slice [OK]

Common Mistakes:

• Ignoring index order in slicing
• Assuming code runs without error
• Overlooking empty string result

5. You want to improve an extractive QA model to handle questions where the answer might not be present in the context. Which approach is best?

hard

A. Use a generative model instead of extractive QA

B. Add a 'no answer' prediction option so the model can say answer is missing

C. Train the model only on questions with guaranteed answers

D. Force the model to always select some text span regardless

Solution

1. Step 1: Understand the problem of missing answers

   Extractive QA models can fail if forced to select an answer when none exists in context.

2. Step 2: Evaluate solution options

   Adding a 'no answer' option lets the model explicitly indicate no answer is found, improving reliability.

3. Final Answer:

   Add a 'no answer' prediction option so the model can say answer is missing -> Option B

4. Quick Check:

   Handle missing answers = add 'no answer' option [OK]

Hint: Allow model to say 'no answer' when context lacks answer [OK]

Common Mistakes:

• Forcing answer selection even if none exists
• Ignoring questions without answers during training
• Switching to generative models unnecessarily