Open-domain QA basics in NLP - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is Open-domain Question Answering (QA)?

Open-domain QA is a system that answers questions on any topic using a large collection of documents or knowledge sources, without being limited to a specific subject area.

beginner

What are the two main steps in an Open-domain QA system?

1. Document Retrieval: Finding relevant documents or passages.
2. Answer Extraction: Selecting the exact answer from those documents.

beginner

Why is document retrieval important in Open-domain QA?

Because it narrows down the huge amount of information to a smaller set of relevant texts, making it easier and faster to find the correct answer.

intermediate

What is a common model type used for answer extraction in Open-domain QA?

Transformer-based models like BERT are commonly used because they understand context well and can find precise answers within text passages.

beginner

How does Open-domain QA differ from Closed-domain QA?

Open-domain QA can answer questions on any topic using large, general knowledge sources, while Closed-domain QA focuses on a specific area with limited data.

What is the first step in an Open-domain QA system?

A Document Retrieval

B Answer Extraction

C Training the model

D Data labeling

The system first finds relevant documents before extracting answers.

Which model type is often used for extracting answers in Open-domain QA?

A Transformer-based models

B Linear Regression

C K-means clustering

D Decision Trees

Transformer models like BERT understand context and extract answers well.

Open-domain QA systems can answer questions about:

A Only legal topics

B Any topic

C Only medical topics

D Only sports topics

Open-domain QA covers any topic using large knowledge sources.

Why is document retrieval necessary in Open-domain QA?

A To label data automatically

B To train the model faster

C To reduce the search space for answers

D To generate questions

Retrieval narrows down documents to find relevant information quickly.

Closed-domain QA differs from Open-domain QA because it:

A Answers questions on any topic

B Uses only images

C Does not use machine learning

D Focuses on a specific subject area

Closed-domain QA specializes in a limited topic or dataset.

Explain the two main steps of an Open-domain QA system and why each is important.

Think about how the system finds and then picks the answer.

Describe how Open-domain QA differs from Closed-domain QA in terms of scope and data.

Consider the range of questions each can answer.

Practice

1. What is the main goal of open-domain question answering (QA)?

easy

A. To summarize a single document

B. To translate text from one language to another

C. To find answers to any question from a large collection of texts

D. To generate new text based on a prompt

Solution

1. Step 1: Understand the definition of open-domain QA

   Open-domain QA aims to answer questions using a wide range of texts, not limited to a specific topic.

2. Step 2: Compare options with this definition

   Only To find answers to any question from a large collection of texts matches this goal; others describe different NLP tasks.

3. Final Answer:

   To find answers to any question from a large collection of texts -> Option C

4. Quick Check:

   Open-domain QA = Finding answers from many texts [OK]

Hint: Open-domain QA means answering questions from many texts [OK]

Common Mistakes:

• Confusing QA with translation
• Thinking QA only summarizes text
• Mixing QA with text generation

2. Which of the following is the correct sequence of steps in an open-domain QA system?

easy

A. Classify questions, then ignore documents

B. Generate answers first, then find documents

C. Summarize documents, then translate answers

D. Retrieve relevant documents, then read and extract answers

Solution

1. Step 1: Recall the typical open-domain QA pipeline

   It first retrieves relevant documents, then reads them to find answers.

2. Step 2: Match options to this pipeline

   Only Retrieve relevant documents, then read and extract answers correctly describes this order; others are incorrect or unrelated.

3. Final Answer:

   Retrieve relevant documents, then read and extract answers -> Option D

4. Quick Check:

   QA steps = Retrieve then read [OK]

Hint: QA first finds texts, then reads for answers [OK]

Common Mistakes:

• Thinking answer generation happens before retrieval
• Confusing summarization with QA
• Ignoring the retrieval step

3. Given this Python snippet using a pretrained QA model:

from transformers import pipeline
qa = pipeline('question-answering')
context = "The Eiffel Tower is in Paris."
question = "Where is the Eiffel Tower located?"
result = qa(question=question, context=context)
print(result['answer'])

What will be printed?

medium

A. Paris

B. Eiffel Tower

C. question-answering

D. The Eiffel Tower

Solution

1. Step 1: Understand the QA pipeline usage

   The pipeline takes a question and context, then returns the answer span from the context.

2. Step 2: Identify the answer span in the context

   The question asks for location; context says "The Eiffel Tower is in Paris." The answer is "Paris".

3. Final Answer:

   Paris -> Option A

4. Quick Check:

   Answer extracted = Paris [OK]

Hint: QA model returns the answer span from context [OK]

Common Mistakes:

• Printing the question instead of answer
• Confusing the model name with output
• Selecting the full sentence instead of answer span

4. You have this code snippet for open-domain QA:

from transformers import pipeline
qa = pipeline('question-answering')
context = "Mount Everest is the highest mountain."
question = "What is the highest mountain?"
result = qa(question=question, context=context)
print(result['answer'])

But it raises a KeyError: 'answer'. What is the likely cause?

medium

A. The context is empty

B. The pipeline was not properly initialized for question-answering

C. The question is not a string

D. The print statement is incorrect

Solution

1. Step 1: Analyze the error KeyError: 'answer'

   This error means the result dictionary does not have the key 'answer'.

2. Step 2: Check pipeline initialization

   If the pipeline is not correctly set for 'question-answering', the output format differs and lacks 'answer'.

3. Final Answer:

   The pipeline was not properly initialized for question-answering -> Option B

4. Quick Check:

   Wrong pipeline type causes missing 'answer' key [OK]

Hint: Ensure pipeline type matches task to get correct keys [OK]

Common Mistakes:

• Assuming context is empty without checking
• Ignoring pipeline initialization errors
• Misreading error as print statement issue

5. You want to improve an open-domain QA system that sometimes returns wrong answers because it reads irrelevant documents. Which approach helps most?

hard

A. Improve the document retrieval step to find more relevant texts

B. Use a smaller pretrained model to speed up reading

C. Remove the retrieval step and read all documents

D. Translate questions to another language before answering

Solution

1. Step 1: Identify the problem cause

   Wrong answers happen because the system reads irrelevant documents.

2. Step 2: Choose the best fix

   Improving retrieval to get relevant documents reduces wrong answers effectively.

3. Final Answer:

   Improve the document retrieval step to find more relevant texts -> Option A

4. Quick Check:

   Better retrieval = better answer relevance [OK]

Hint: Better retrieval means better answers [OK]

Common Mistakes:

• Thinking smaller models improve accuracy
• Removing retrieval causes overload and noise
• Translating questions doesn't fix relevance