This repository provides course materials of the Natural Language Processing course at NTHU (instructor: Prof. Hung-Yu Kao).
| TA Hour | |
|---|---|
| Mon. | 15:30 - 16:30 |
| Wed. | 15:30 - 16:30 |
| Location | 炯朗館(資電館) 635 |
TA email: nthuikmlab@gmail.com
Slido:Slido
| Week | Topics | Slide | Video | HW |
|---|---|---|---|---|
| W1 | 課程簡介 Syllabus / Introduction to NLP | Slide Slide1 |
Video1 Video2 |
|
| W2 | 自然語言處理簡介 (1/2) Introduction to NLP (vector space, indexing, parts of speech, phrase structure) | Slide2 |
Video1 Video2 |
HW1 Video |
| W3 | 自然語言處理簡介 (2/2) Introduction to NLP (Language model) | Slide3A |
Video1 Video2 |
|
| W4 | 基礎文字資料機器學習 (1/2) Basic machine learning for text (Text Classification, NB, NN) | SlideTA Slide3B |
Video1 Video2 |
|
| W5 | 基礎文字資料機器學習 (2/2) Basic machine learning for text (word embedding, text representation) | Slide3C |
Video1 Video2 |
HW2 Video |
| W6 | 文字生成式AI簡介(1/3) Introduction to GAI (text): Word Embeddings, Language Modeling (RNN), Sequence-to-sequence Models, and Attention Mechanisms, Sub-word Tokenization; Transformers | Slide4 |
Video1 Video2 |
|
| W7 | Python for text tutorial (1/2) | Slide5 SlideTA |
Video1 Video2 Video(HuggingFace Tutorial) |
|
| W8 | Python for text tutorial (2/2) | Slide6 |
Video1 Video2 |
HW3 Video |
| W9 | 文字生成式AI簡介(2/3) Introduction to GAI (text): ELMo, BERT, GPT, and T5 (BERT and its Family) | SlideTA Slide7 |
Video1 Video2 |
|
| W10 | 文字生成式AI簡介(3/3) Introduction to GAI (text): Decoding Strategies and Evaluations for Natural Language Generation | Slide8 |
Video1Video2 |
|
| W11 | 大語言模型簡介與訓練 (1/3): Large language model concept and training (GPT-3, InstructGPT, RLHF) | |||
| W12 | 大語言模型簡介與訓練 (2/3): Parameter Efficient Fine-Tuning (PEFT) | |||
| W13 | 大語言模型簡介與訓練 (2/3): Introduction and Review technique of Retrieval Augmented Generation (RAG) | |||
| W14 | Term project presentation (1/3) | |||
| W15 | Term project presentation (1/3) | |||
| W16 | Term project presentation (1/3) | |||
| W17 | Term Project (demo) (optional) | |||
| W18 | Term Project (demo) (optional) |
- Italics: Tutorial; Bold: Reporting