|
AI539: Advanced Information Retrieval – Spring 2025
Course Description
This course covers the foundations and recent advancements of Information Retrieval (IR). The course focues on the design and implementation of text-based information systems such as search engine and recommender systems. We will covers topics including crawling and indexing, query understanding, (large) language models, learning to rank, interactive search, evaluation and user models, question answering, conversational system, and neural models for IR.
Course Information
Lectures
Tuesday & Thursday 4:00-5:20pm at Weniger Hall 201
Instructor
Huazheng Wang
Email: huazheng.wang [at] oregonstate.edu
Office: KEC 3097
Office hours: Tuesday 2-4pm, KEC 3097
Contact
We will use Canvas for posting slides and assignments, and Discord for communication. See Canvas announcements for the link to Discord channel.
Prerequisites
Python. We will use Python/Jupyter notebook for programming assignments.
Basic knowledge of probability and statistics.
Basic understanding of machine learning / deep learning.
Schedule
| Week | Date | Lecture | Readings |
| Week 1 | 4/1 | Introduction to the course, Information retrieval basics | [MRS] Ch 1. |
| 4/3 | Web crawling, text processing, inverted index | [MRS] Ch 2, Ch 20, Ch 4. |
| Week 2 | 4/8 | Vector space models and probabilistic retrieval models | [MRS] Ch 6, Ch 11. |
| 4/10 | IR evaluations and metrics | [MRS] Ch 8. |
| Week 3 | 4/15 | Language models | [MRS] Ch 6, Ch 11. |
| 4/17 | Learning to rank | [MRS] Ch 12. |
| Week 4 | 4/22 | Relevance feedback, implicit feedback and click model | [MRS] Ch 13, Ch 14. |
| 4/24 | Neural IR and distributed representation learning for text | |
| Week 5 | 4/29 | Neural ranking models and Dense retrieval | |
| 5/1 | Large Language Model | |
| Week 6 | 5/6 | Question answering and conversational system | |
| 5/8 | Recommender system and Information filtering | |
| Week 7 | 5/13 | Midterm Exam | |
| 5/15 | Retrieval-Augmented Generation | |
| Week 8 | 5/20 | Agentic System (Guest lecture) | |
| 5/22 | Reinforcement Learning from Human Feedback | |
| Week 9 | 5/27 | Unbiasedness, fairness and robustness in IR | |
| 5/29 | Interactive information retrieval and online learning | |
| Week 10 | 6/3 | Project presentations | |
| 6/5 | Project presentations |
|
Gradings
Homework – (2*15%) 30%
Midterm - 20%
Paper presentation – 10%
Final project – 40%
Total – 100%
Resources
Readings:
[MRS] Introduction to Information Retrieval. Christopher D. Manning, Prabhakar Raghavan, and Hinrich Schuetze, Cambridge University Press, 2008.
|