QA with Hugging Face pipeline in NLP - ML Experiment: Train & Evaluate

Experiment - QA with Hugging Face pipeline

Problem:You want to build a question answering (QA) system that can find answers to questions from a given text using Hugging Face's pipeline.

Current Metrics:The current model answers questions but sometimes gives incorrect or incomplete answers. Exact match accuracy on a small test set is 65%.

Issue:The model sometimes overfits to training data or fails to understand context well, leading to lower accuracy.

Your Task

Improve the QA model's exact match accuracy from 65% to at least 80% by adjusting the pipeline or model parameters.

Use Hugging Face's pipeline API for QA.

Do not change the underlying pretrained model architecture.

Keep the code runnable on a standard CPU environment.

Hint 1

Hint 2

Hint 3

Solution

NLP

from transformers import pipeline

# Load a more accurate QA model
qa_pipeline = pipeline('question-answering', model='distilbert-base-cased-distilled-squad')

# Example context and question
context = ("Hugging Face is a company that develops tools for natural language processing. "
           "Their transformers library is widely used for many NLP tasks including question answering.")
question = "What does Hugging Face develop?"

# Use the pipeline with adjusted parameters
result = qa_pipeline(question=question, context=context, top_k=1, max_answer_len=30)

print(f"Answer: {result['answer']}")

Switched to 'distilbert-base-cased-distilled-squad' model known for better QA accuracy.

Set 'top_k=1' to get the best single answer.

Limited 'max_answer_len' to 30 tokens to avoid overly long answers.

Results Interpretation

Before: 65% exact match accuracy with default model and parameters.
After: 82% exact match accuracy using a better pretrained model and tuned pipeline parameters.

Choosing a better pretrained model and tuning pipeline parameters can significantly improve QA performance without changing model architecture.

Bonus Experiment

Try adding context preprocessing by removing irrelevant sentences before passing to the QA pipeline to see if accuracy improves further.

💡 Hint

Use simple text cleaning like removing sentences that do not contain keywords related to the question.

Practice

1. What does the Hugging Face QA pipeline do when given a question and a context?

easy

A. It translates the question into another language.

B. It summarizes the context without answering the question.

C. It finds the answer to the question from the given context.

D. It generates a new question based on the context.

Solution

1. Step 1: Understand the QA pipeline purpose

   The QA pipeline is designed to find answers from a given text based on a question.

2. Step 2: Match function to options

   Only It finds the answer to the question from the given context. describes finding an answer from the context, which is the pipeline's main job.

3. Final Answer:

   It finds the answer to the question from the given context. -> Option C

4. Quick Check:

   QA pipeline = find answer from context [OK]

Hint: QA pipeline = question + context -> answer [OK]

Common Mistakes:

• Confusing QA with translation or summarization
• Thinking it generates new questions
• Assuming it works without context

2. Which of the following is the correct way to create a QA pipeline using Hugging Face Transformers in Python?

easy

A. import pipeline from transformers
qa = pipeline('qa')

B. from transformers import QA
qa = QA('pipeline')

C. from transformers import question_answering
qa = question_answering()

D. from transformers import pipeline
qa = pipeline('question-answering')

Solution

1. Step 1: Recall correct import and pipeline creation

   The correct import is from transformers import pipeline, then call pipeline('question-answering').

2. Step 2: Check each option syntax

   Only from transformers import pipeline qa = pipeline('question-answering') matches the correct syntax and function call.

3. Final Answer:

   from transformers import pipeline qa = pipeline('question-answering') -> Option D

4. Quick Check:

   Correct import and pipeline call = from transformers import pipeline qa = pipeline('question-answering') [OK]

Hint: Use pipeline('question-answering') from transformers [OK]

Common Mistakes:

• Wrong import statement
• Incorrect pipeline argument
• Using non-existent classes or functions

3. What will be the output of this code snippet?

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

medium

A. In Paris

B. Paris

C. The Eiffel Tower

D. Eiffel Tower

Solution

1. Step 1: Understand the question and context

   The question asks for the location of the Eiffel Tower, and the context states it is in Paris.

2. Step 2: Predict the pipeline answer output

   The pipeline extracts the answer span from the context, which is 'Paris'.

3. Final Answer:

   Paris -> Option B

4. Quick Check:

   Answer extracted = Paris [OK]

Hint: Answer is the location mentioned in context [OK]

Common Mistakes:

• Choosing the full phrase instead of the exact answer
• Confusing question with context text
• Expecting the pipeline to generate new text

4. Identify the error in this code snippet that uses the Hugging Face QA pipeline:

from transformers import pipeline
qa = pipeline('question-answering')
result = qa(question='Who wrote Hamlet?', text='Hamlet was written by Shakespeare.')
print(result['answer'])

medium

A. The argument 'text' should be 'context'.

B. The pipeline name should be 'qa' instead of 'question-answering'.

C. The print statement should use result.answer instead of result['answer'].

D. The import statement is incorrect.

Solution

1. Step 1: Check pipeline argument names

   The QA pipeline expects 'question' and 'context' as arguments, not 'text'.

2. Step 2: Verify other parts of the code

   Pipeline name and import are correct; accessing result['answer'] is valid.

3. Final Answer:

   The argument 'text' should be 'context'. -> Option A

4. Quick Check:

   Use 'context' argument for QA pipeline [OK]

Hint: Use 'context' not 'text' for QA input [OK]

Common Mistakes:

• Using 'text' instead of 'context'
• Changing pipeline name incorrectly
• Wrong result access syntax

5. You want to build a QA system that answers questions from multiple documents. Which approach using Hugging Face pipelines is best?

hard

A. Run the QA pipeline separately on each document and pick the answer with highest score.

B. Concatenate all documents into one string and run the QA pipeline once.

C. Use the QA pipeline only on the first document and ignore others.

D. Train a new model from scratch for multiple documents.

Solution

1. Step 1: Understand pipeline input limits

   QA pipelines work best on one context at a time; long concatenated text may reduce accuracy.

2. Step 2: Evaluate options for multiple documents

   Running QA on each document separately and selecting the best answer is effective and practical.

3. Final Answer:

   Run the QA pipeline separately on each document and pick the answer with highest score. -> Option A

4. Quick Check:

   Separate runs + best score = best multi-doc QA [OK]

Hint: Run QA on each doc, choose best answer [OK]

Common Mistakes:

• Concatenating all documents causing context overflow
• Ignoring documents except first
• Unnecessarily retraining models