A society grows great when old people plant trees in which shades they shall never sit in.
Found on Internet
This is a bachelor-level course in Natural Language Processing (NLP) offered at Ukrainian Catholic University. The course provides a comprehensive introduction to the fundamental concepts, techniques, and applications of NLP, covering both classical and modern approaches to language processing.
Students will learn to:
- Understand core NLP tasks and real-world use cases
- Implement classical NLP pipelines and preprocessing techniques
- Apply neural network approaches to language processing
- Work with modern transformer-based models and fine-tuning techniques
- Understand how to create and evaluate NLP models and pipelinesusing popular libraries
YouTube playlist: https://www.youtube.com/playlist?list=PLF5C4LaYzP2LCKeTTgXJgFoXaDDn2COEp
| Session | Topic | Type | Lecturer | Materials | Video Recording 🇺🇦 |
|---|---|---|---|---|---|
| 1 | Introduction to the course. NLP tasks and use cases | Lecture | Viktoriia Makovska | Lecture 1 PDF | Not available :( |
| 2 | Classical NLP. | Lecture | Yurii Paniv | Lecture 2 PDF |  |
| 1 | Classical NLP | Practice | Yurii Paniv |  |
|
| 3 | Transition to Modern Machine Learning | Lecture | Maksym Shamrai | Lecture 3 PDF | |
| 2 | PyTorch Basics, Classification Task | Practice | Maksym Shamrai | |
|
| 4 | Transformer Anatomy. | Lecture | Yurii Laba | Lecture 4 PDF | |
| 3 | PyTorch, RNN. | Practice | Maksym Shamrai | |
|
| 5 | Applied NLP Tasks (Part 1) | Lecture | Viktoriia Makovska | Lecture 5 PDF | |
| 4 | Neural Machine Translation (Seq2Seq) | Practice | Yurii Paniv | |
|
| 6 | Applied NLP Tasks (Part 2) | Lecture | Yurii Paniv | Lecture 6 PDF | |
| 5 | Sequence Labelling | Practice | Yurii Paniv | NER Sequence Labelling |
|
| 7 | Evaluation in NLP | Lecture | Yurii Laba | Lecture 7 PDF | |
| 6 | Data Annotation for NLP tasks | Practice | Dmytro Chaplynskyi | Practice 6 PDF More materials in video |
|
| 8 | Data Processing & Mining | Lecture | Dmytro Chaplynskyi | Lecture 7_1 PDF Lecture 8 PDF | |
| 7 | Data Processing & Mining | Practice | Dmytro Chaplynskyi | Materials in video | |
| 9 | Large Language Models (LLMs) | Lecture | Yurii Paniv | Lecture 9 PDF | |
| 8 | Tokenizers | Practice | Maksym Shamrai | |
|
| 9 | Fine-tuning Sentence Transformers. Pytorch Lightning and SetFit | Practice | Yurii Paniv | PyTorch Lightning SetFit |
|
| 10 | Parameter-efficient fine-tuning LLMs | Practice | Yurii Paniv | |
|
| - | Semester project status update | Presentation | Viktoriia Makovska + Yurii Paniv | ||
| 10 | Prompt Engineering. | Lecture | Viktoriia Makovska | Lecture 10 PDF | |
| 11 | LoRA in depth | Practice | Yurii Paniv | |
|
| 11 | Information Retrieval | Lecture | Dmytro Chaplynskyi | Lecture 11 PDF | |
| 12 | Retrieval-Augmented Generation (RAG) | Practice | Viktoriia Makovska | Practice 12 PDF | |
| 12 | MultiModal Models | Lecture | Yurii Laba | Lecture 12 PDF | |
| 13 | Multimodal Retrieval with CLIP | Practice | Yurii Laba | |
|
| 13 | Deployment. Performance. Quantization | Lecture | Maksym Shamrai | Lecture 13 PDF | |
| 14 | Safety, Alignment, Ethics | Lecture | Viktoriia Makovska | Lecture 14 PDF | |
| - | Semester project presentation | Presentation | Yurii Paniv + Viktoriia Makovska |
Looking forward for your feedback! Please open an issue here what we need to improve.
Kudos to the team:
Classic NLP course by Jurafsky and Martin: https://web.stanford.edu/~jurafsky/slp3/
https://naviglinlp.blogspot.com/p/natural-language-processing-basic.html