COURSE OVERVIEW
Introduction to NLP
• What is Natural Language Processing?
• Importance and Applications of NLP
• Traditional NLP vs DL-based NLP
• Challenges in NLP
Text Data Basics
• Structure of Text Data
• Corpus, Tokens, Sentences, Documents
• Bag of Words vs TF-IDF
• Stopwords, Lemmatization, Stemming
• Regular Expressions for Text Cleaning
• Text Normalization Techniques
• N-grams and their Role
Text Preprocessing Techniques
• Tokenization
• Lowercasing and Punctuation Removal
• Stopword Removal
• Stemming vs Lemmatization
• Removing Special Characters and Numbers
• Padding and Truncation
• Word Frequency and Vocabulary Creation
Feature Extraction from Text
• CountVectorizer
• TF-IDF Vectorizer
• Word Embeddings Overview
• Word2Vec
• GloVe
• FastText
• Embedding Layer in Keras
Text Classification and NLP Models
• Sentiment Analysis
• Spam Detection
• News Topic Classification
• Named Entity Recognition (NER)
• POS Tagging
• Text Summarization (Extractive)
Sequence Models for NLP
• Recurrent Neural Networks (RNNs) for Text
• LSTM and GRU
• Bidirectional RNNs
• Attention Mechanism
• Sequence-to-Sequence Models (Seq2Seq)
• Encoder-Decoder Architecture
Advanced NLP Tasks
• Text Generation
• Text Summarization (Abstractive)
• Machine Translation
• Question Answering
• Semantic Similarity
• Zero-shot and Few-shot NLP
NLP Evaluation Metrics
• Accuracy, Precision, Recall, F1 Score
• BLEU Score
• ROUGE Score
• Perplexity
• Confusion Matrix for Text Tasks
Project Ideas
• Sentiment Analysis Web App
• Resume Parser
• FAQ Chatbot using Transformers
• News Headline Classifier
• Text Summarizer for Articles
• Language Detection Tool
Deployment of NLP Models
• Exporting NLP Models using Pickle/Joblib
• Streamlit or Flask-based NLP Web Apps
• Deploying NLP Models on Cloud (GCP, AWS, HuggingFace Spaces)
• API Deployment with FastAPI
Responsible NLP and Ethics
• Bias in Language Models
• Toxic Content and Mitigation
• Privacy in Text Data
• Explainability in NLP Models
• Fairness in NLP Applications
Course Outcomes
- Understand the fundamentals of language processing and linguistic concepts.
- Apply text preprocessing techniques such as tokenization, stemming, and lemmatization.
- Implement models for text classification, sentiment analysis, and sequence labeling.
- Use word embeddings and transformer-based models for NLP tasks.
- Develop applications like chatbots, text summarization, and machine translation.
- Evaluate NLP models using appropriate metrics and improve performance.
