資訊檢索與擷取
Generative Information Retrieval
| 節 | 週二 |
|---|---|
5 13:20–14:10 | 資訊檢索與擷取 EC115 2 節連堂 |
6 14:20–15:10 |
* 根據陽明交大上課時間表所列
This course introduce the fundamental concepts and techniques of Information Retrieval (IR) and its pivotal role within the natural language processing (NLP) domain. The emphasis will be on understanding how computer systems can efficiently and effectively retrieve text-based information in response to user queries. A significant portion of the course will be dedicated to exploring the application of IR. Additionally, students will be introduced to advanced frameworks like retrieval-augmented generation (RAG) that merge the power of large language models (LLMs) with external knowledge to achieve more accurate and informed outputs.
Machine Learning, Python Programming
3 homework, 1 final term project, 1 group presentation No exam (This course does not have mid-term or final exams, and there are no classes during mid-term and final exam weeks.)
| 週次 | 主題 |
|---|---|
| 第 1 週 | Introduction of the Course |
| 第 2 週 | Introduction to Information Retrieval |
| 第 3 週 | Break for Moon Festival |
| 第 4 週 | Classical retrieval models (scoring, term weighting, and vector space model) |
| 第 5 週 | Probabilistic IR (BM25 and Latent Semantic Indexing) |
| 第 6 週 | Evaluation methods |
| 第 7 週 | Fundamental of Information Extraction |
| 第 8 週 | Midterm (No class) |
| 第 9 週 | Fundamentals of Deep Learning |
| 第 10 週 | Deep Learning in IR |
| 第 11 週 | Break for EMNLP |
| 第 12 週 | Multimodal Information Retrieval |
| 第 13 週 | Introduction to Generative AI |
| 第 14 週 | Prompt Engineering |
| 第 15 週 | Retrieval-Augmented Generation |
| 第 16 週 | Final exam (No class) |
Introduction to Information Retrieval, by C. Manning, P. Raghavan, and H. Schütze (Cambridge University Press, 2008).
- 時間
- by appointment