Content

This course explores the field of intelligent information retrieval, from foundational and traditional methods to modern approaches such as the use of large language models. Topics covered in this course include:

1. Overview of Text Retrieval
2. Retrieval Models
3. Evaluation in Information Retrieval
4. Statistical Language Models & Language Models for Text Retrieval
5. Feedback in Information Retrieval
6. Web
7. Learning to Rank
8. Neural Information Retrieval
9. LLMs for Information Retrieval

In this course, alongside theoretical foundations, special emphasis is placed on practical aspects as well. Through hands-on exercises and applied projects using Python, students will acquire the skills needed to implement and evaluate information retrieval methods. The ultimate goal is to enable students to leverage data-driven approaches for knowledge extraction and for enhancing intelligent search and decision-making processes.

Logistics

Format

This course is primarily offered in a classroom setting, held twice weekly on Sundays and Tuesdays from 13:30 to 15:00. On special occasions, online classes may be conducted using Elearn Platform - students will be notified in advance.

Workload Expectation

Students can expect 6 computer/theory-based assignments over the duration of the course, with workload varying based on subject complexity. Additionally, students will deliver one paper presentation. Supplementary self-study outside of lecture times will be required to excel in this rigorous graduate course.

Textbook & Resources

• Homework Template

Contact Information

• shakery@ut.ac.ir - Dr. Azadeh Shakery, Instructor
• erfanshahabi@outlook.com - Erfan Shahabi, Head TA