🧠 Natural Language Processing

This repository contains my solutions and implementations for a university-level Natural Language Processing (NLP) course.

The project consists of 10 exercise sheets, each covering fundamental and advanced NLP concepts using Python, NLTK, and related libraries.

---

📚 Course Topics Covered

Throughout the exercises, the following NLP concepts were explored:

📝 Text Processing

• Tokenization
• Normalization
• Stopword removal
• Stemming & Lemmatization
• Regular expressions

📊 Language Modeling

• N-gram models
• Probability estimation
• Perplexity evaluation

🏷 Part-of-Speech Tagging

• POS tagging with NLTK
• Tagging accuracy evaluation

🌳 Syntax & Parsing

• Context-Free Grammars (CFG)
• Constituency parsing
• Tree representations

📚 Word Representations

• Word frequency analysis
• Distributional semantics
• Vector representations

🤖 Machine Learning for NLP

• Text classification
• Feature extraction
• Evaluation metrics (accuracy, precision, recall, F1)

🔍 Advanced Topics

• Named Entity Recognition (NER)
• Sequence labeling
• Corpus processing

---

Each exercise sheet is provided in:

• 📓 Notebook version (.ipynb) – interactive exploration
• 🐍 Python script version (.py) – standalone implementation

---

🚀 Getting Started

1️⃣ Requirements

• Python 3.9+
• Jupyter Notebook
• Required libraries:

pip install nltk numpy pandas scikit-learn matplotlib

If needed, download NLTK resources:

import nltk
nltk.download('all')

---

2️⃣ Run Notebooks

jupyter notebook

Open any Exercise_Sheet_X.ipynb.

---

🎯 Learning Outcomes

• Practical experience with core NLP pipelines
• Understanding of probabilistic language models
• Working with real corpora
• Implementing ML models for text classification
• Evaluating NLP systems properly

---

📄 License

This repository contains coursework implementations and is shared for educational purposes only.