Open-domain QA basics in NLP - Model Pipeline Trace

Model Pipeline - Open-domain QA basics

This pipeline answers questions by searching a large collection of documents and then selecting the best answer. It first finds relevant text pieces, then reads them carefully to find the exact answer.

Data Flow - 5 Stages

1Input Question

1 question string→Receive a natural language question from user→1 question string

"What is the capital of France?"

↓

2Document Retrieval

1 question string→Search a large text database to find top relevant documents or passages→5 passages x 100 words each

["Paris is the capital city of France...", "France's largest city is Paris..."]

↓

3Context Preparation

5 passages x 100 words each→Combine retrieved passages into a single context for reading→1 context string (~500 words)

"Paris is the capital city of France. It is known for... France's largest city is Paris..."

↓

4Answer Extraction Model

1 question string + 1 context string→Use a reading comprehension model to find answer span in context→1 answer string

"Paris"

↓

5Output Answer

1 answer string→Return the extracted answer to the user→1 answer string

"Paris"

Training Trace - Epoch by Epoch

Loss
1.2 |****
1.0 |*** 
0.8 |**  
0.6 |*   
0.4 |    
     +----
      1 2 3 4 5 Epochs

Epoch	Loss ↓	Accuracy ↑	Observation
1	1.2	0.45	Model starts learning to locate answers in text.
2	0.9	0.60	Model improves understanding of question and context.
3	0.7	0.72	Model better identifies correct answer spans.
4	0.5	0.80	Model converges with good answer extraction ability.
5	0.4	0.85	Final fine-tuning improves accuracy slightly.

Prediction Trace - 5 Layers

Layer 1: Input Question

Layer 2: Document Retrieval

Layer 3: Context Preparation

Layer 4: Answer Extraction Model

Layer 5: Output Answer

Model Quiz - 3 Questions

What is the main role of the Document Retrieval stage?

A Generate the final answer directly

B Find relevant text passages related to the question

C Combine passages into one context

D Train the model to understand questions

Key Insight

Open-domain QA works by first finding relevant information, then carefully reading it to pick the exact answer. Training improves the model's ability to locate answers, shown by decreasing loss and increasing accuracy.

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