NLP_AI_Revision

What is NLP, and why is it important?
Q: Define NLP and its applications.
A: NLP enables machines to understand, interpret, and generate human language. Applications include:

Chatbots: Conversational AI (e.g., customer support).
Translation: Tools like Google Translate.
Sentiment Analysis: Analyzing user opinions on social media.
Text Summarization: Creating concise versions of articles.
2. What are key challenges in NLP?
Q: Why is NLP considered difficult?
A: Challenges include:

Ambiguity: Words with multiple meanings (e.g., "bank").
Context understanding: Resolving references and idioms.
Data diversity: Handling multiple languages or dialects.
Lack of labeled data: Training data scarcity for specific tasks.
3. What is Named Entity Recognition (NER)?
Q: How does NER work?
A: NER identifies entities like names, dates, and locations in text. For example:

Input: "Barack Obama was born in Hawaii."
Output: {Person: Barack Obama, Location: Hawaii}
4. What are transformers in NLP?
Q: Explain the role of transformers in NLP.
A: Transformers revolutionized NLP by using attention mechanisms to process text sequences efficiently. Models like BERT and GPT are based on transformers.

5. How do BERT and GPT differ in NLP tasks?
Q: When should BERT or GPT be used?
A:

BERT: Bidirectional model for understanding context, ideal for classification and Q&A.
GPT: Autoregressive model for generating coherent text, suitable for creative writing.
Artificial Intelligence (AI)
6. What is AI?
Q: Define AI in simple terms.
A: AI is the science of creating machines that perform tasks requiring intelligence, like reasoning, learning, and decision-making.

7. How does AI differ from Machine Learning (ML)?
Q: Are AI and ML the same?
A: ML is a subset of AI focused on algorithms that learn from data. AI is broader, encompassing ML, NLP, robotics, and more.

8. What are supervised, unsupervised, and reinforcement learning?
Q: Explain the types of learning in AI.
A:

Supervised Learning: Learning with labeled data (e.g., spam detection).
Unsupervised Learning: Learning from unlabeled data (e.g., clustering).
Reinforcement Learning: Learning through trial and error (e.g., teaching a robot to walk).
9. What is explainable AI (XAI)?
Q: Why is explainability important in AI?
A: XAI ensures that AI decisions are interpretable, building trust in applications like healthcare or autonomous driving.