AID405 Natural Language Processing

Referencing Curricula Print this page

Course Code Course Title Weekly Hours* ECTS Weekly Class Schedule
T P
AID405 Natural Language Processing 3 2 6
Prerequisite None It is a prerequisite to

None

Lecturer Office Hours / Room / Phone

Currently not available

E-mail
Assistant Assistant E-mail
Course Objectives By the end of this course, students will be able to:

1. Explain the recent developments and innovations in natural language processing and their applications in various domains.
2. Implement and evaluate different types of natural language processing models using Python and its libraries.
3. Apply natural language processing models to solve real-world problems of interest.
4. Explore and research advanced topics in natural language processing and present their findings.
Textbook The required textbooks for this course are: [1] Vajjala, S., Gupta, A., Majumder, B., & Surana H. (2020). Practical Natural Language Processing: A Comprehensive Guide to Building Real-World NLP Systems. O’Reilly Media. [2] Jurafsky, D., & Martin J.H. (2019). Speech and Language Processing (3rd ed.). Prentice Hall.
Additional Literature
  • The recommended textbooks for this course are:
  • [1] Manning C.D., & Schütze H. (1999). Foundations of Statistical Natural Language Processing. MIT Press.
  • [2] Goldberg Y. (2017). Neural Network Methods for Natural Language Processing. Morgan & Claypool Publishers.
Learning Outcomes After successful  completion of the course, the student will be able to:
  1. Explain the recent developments and innovations in natural language processing and their applications in various domains.
  2. Implement and evaluate different types of natural language processing models using Python and its libraries.
  3. Apply natural language processing models to solve real-world problems of interest.
  4. Explore and research advanced topics in natural language processing and present their findings.
Teaching Methods There will be a 1 hour of theory and explaining the background of the topic, then we will continue with the programming and practice
Teaching Method Delivery Face-to-face Teaching Method Delivery Notes
WEEK TOPIC REFERENCE
Week 1 Introduction to Natural Language Processing PNLPP: Ch. 1; SLP: Ch. 1
Week 2 Text Processing and Regular Expressions Assignment 1: Text Processing with NLTK PNLPP: Ch. 2; SLP: Ch. 2
Week 3 Language Modeling and Text Classification PNLPP: Ch. 3; SLP: Ch. 3 & 4
Week 4 Information Extraction and Named Entity Recognition Assignment 2: Information Extraction and Named Entity Recognition with spaCy PNLPP: Ch. 4; SLP: Ch. 5 & 7
Week 5 Machine Translation and Sequence-to-Sequence Models PNLPP: Ch. 5; SLP: Ch. 10 & 11
Week 6 Word Embeddings and Neural Language Models Assignment 3: Word Embeddings and Neural Language Models with PyTorch PNLPP: Ch.6; SLP: Ch.6
Week 7 Midterm exam
Week 8 Transformers and Contextualized Embeddings PNLPP: Ch.7; SLP: Ch.12
Week 9 Natural Language Generation and Text Summarization Assignment 4: Natural Language Generation with Hugging Face Transformers PNLPP: Ch.8; SLP: Ch.23
Week 10 Dialogue Systems and Chatbots PNLPP: Ch.9; SLP: Ch.24
Week 11 Advanced Topics in Natural Language Processing (I) - Self-Supervised Learning and Contrastive Learning Assignment 5: Self-Supervised Learning and Contrastive Learning with PyTorch Lightning PNLPP: Ch.10
Week 12 Advanced Topics in Natural Language Processing (II) - Graph Neural Networks and Geometric Deep Learning PNLPP: Ch.11
Week 13 Advanced Topics in Natural Language Processing (III) - Meta-Learning and Few-Shot Learning Assignment 6: Meta-Learning and Few-Shot Learning with Reptile PNLPP: Ch.12
Week 14 Advanced Topics in Natural Language Processing (IV)- Large Language Models Hands-on
Week 15 Final Project Presentations and Course Summary and Feedback
Assessment Methods and Criteria Evaluation Tool Quantity Weight Alignment with LOs
Final Exam 1 30
Semester Evaluation Components
Midterm 1 25
Quizzes 3 15
Project and presentation 1 15
Assignments 6 15
***     ECTS Credit Calculation     ***
 Activity Hours Weeks Student Workload Hours Activity Hours Weeks Student Workload Hours
Lecture hours 3 14 42 Assignments 3 7 21
Active labs 2 14 28 Home study 1 14 14
In-term exam study 10 1 10 Final exam study 11 1 11
Term project/presentation 2 12 24
        Total Workload Hours = 150
*T= Teaching, P= Practice ECTS Credit = 6
Course Academic Quality Assurance: Semester Student Survey Last Update Date: 01/09/2023

Print this page