Course Overview
This advanced Natural Language Processing (NLP) course explores the interaction between computers and human language, focusing on both the theoretical underpinnings and practical applications of the field. Students will engage with core NLP techniques, including machine learning and deep learning models, to develop skills in text processing, analysis, and translation. The curriculum emphasizes critical thinking about ethical issues such as algorithmic bias and social impacts of NLP technologies. Through lectures, hands-on labs with Python and NLP libraries like TensorFlow and PyTorch, and a capstone project, students will gain the expertise necessary for careers or research in language processing technologies.
- Appointment: Request by Email.
- Lectures: Once a week (Tuesday @11:00 AM – 12:30 PM).
- Credits: 6
- Prerequisites:
- Background in machine learning, statistics, and linear algebra.
- Proficiency in Python.
- Course Website: https://ismaelali.net/?page_id=751
Course Outline
- Overview and Evolution to NLP
- Basic Text Processing and Analysis
- Statistical Modeling of Language
- Machine Learning for NLP
- Deep Learning in NLP
- Natural Language Generation
- Applications of NLP
- Ethics and Future Directions
Course Learning Outcomes
- Understand NLP Fundamentals: Explain key concepts and theories in natural language processing.
- Apply Machine Learning: Use machine learning and deep learning in NLP tasks.
- Develop NLP Applications: Implement applications like text analysis, translation, and speech recognition.
- Analyze Text Data: Process and extract insights from large text datasets.
- Evaluate NLP Models: Assess model performance and understand ethical implications.
- Conduct Research: Perform independent research to solve advanced NLP problems.
- Communicate Findings: Present complex NLP concepts and results effectively.
Course Schedule
| Week | Topic |
| 1 | Introduction to NLP Course overview and logistics Introduction to the field of Natural Language Processing |
| 2 | Text Processing Basics Tokenization, stemming, lemmatization Part-of-speech tagging and named entity recognition |
| 3 | Text Processing Advanced Syntactic parsing and dependency analysis Introduction to semantic analysis |
| 4 | Statistical NLP Probabilistic language models (n-grams, smoothing) Information extraction basics |
| 5 | Machine Learning for NLP Overview of supervised vs unsupervised learning Feature engineering and dimensionality reduction |
| 6 | Deep Learning Fundamentals Introduction to neural networks Basic neural network architectures for NLP |
| 7 | Midterm Exam |
| 8 | Deep Learning in NLP Sequence modeling: RNNs, GRUs, and LSTMs Introduction to Transformers and attention mechanisms |
| 9 | Natural Language Generation I Generating text: techniques and challenges |
| 10 | Natural Language Generation II Advanced NLG applications, dialogue systems, automated storytelling |
| 11 | Applications of NLP I Machine translation and multilingual NLP Speech recognition technologies |
| 12 | Applications of NLP II Question answering systems and chatbots Sentiment analysis and text classification |
| 13 | Ethics and Impacts Discussion on bias, fairness, and ethical issues in NLP Future directions and the societal impact of NLP |
| 14 | Final Exam + Project Presentations |
Course Assessment
- Assignments (10%): Four assignments involving coding and problem-solving in NLP.
- Paper Presentations (20%): Students will present summaries and critiques of assigned research papers.
- Midterm Exam (20%): In-class, covering all material up to the exam.
- Final Exam (50%): In-class, covering all material of the course.
Course Materials
- Reading:
- D. Jurafsky and J. H. Martin. Speech and Language Processing (3rd ed. draft).
- Y. Goldberg. A Primer on Neural Network Models for Natural Language Processing.
- Jacob Eisenstein. Natural Language Processing.
- Resources:
- Tools:
- Python: The primary programming language for the course. Python Official Site
- NLTK (Natural Language Toolkit): A Python library for working with human language data. NLTK Project Page
- spaCy: Advanced NLP library for performance and scalability. spaCy Official Site
- TensorFlow and PyTorch: Frameworks for deep learning applications. TensorFlow Official Site , PyTorch Official Site
- Gensim: Library for unsupervised topic modeling and natural language processing. Gensim GitHub Repository
- Scikit-learn: Machine learning library for Python. Scikit-learn Official Site
- Hugging Face Transformers: Library of pre-trained models for NLP tasks. Hugging Face Transformers
- Jupyter Notebook: Tool for creating and sharing documents that contain live code, visualizations, and narrative text. Jupyter Project Page
Teaching Methods
The course combines theoretical lectures with hands-on lab sessions, using modern NLP tools to apply concepts in practice. Interactive discussions and student-led paper presentations will deepen understanding and engagement with current research. Group projects encourage collaboration and practical problem-solving. Additional online resources and tutorials support self-paced, deeper exploration of topics.
Course Policy
- Illness: If you are absent due to illness as a valid excuse, please notify me of your situation at ismael.ali@edu.krd.edu before (or immediately after) your absence.
- Course and Exam Schedule: Student is responsible of constantly following up the schedule for any updated material or any type of assessments, such as exams/projects.
- Etiquette: Attend all the session to be able comprehending the course material. Submit all assignments on-time, no excuse for late submission, except valid illness report.
- Late Attendance: No student should enter the hall 10 minutes after start time of the session.
- Late Work Policy: Assignments submitted late will incur a penalty of 10% per day, up to a maximum of 5 days. After 5 days, late submissions may not be accepted without prior approval from the instructor.
- Academic Integrity and honesty: All students are expected to adhere to the highest standards of academic integrity. Plagiarism, cheating, or any form of dishonesty will not be tolerated. Violations may result in penalties, including a failing grade or further disciplinary actions.