Admission requirements
Basic prior knowledge of data structures, machine learning, probability theory, text representation (embeddings), linear algebra (vector spaces) is recommended. For students starting in February, it is advised to take this course in the second year of the master and not in the first semester.
Description
The internet, search engines, and large language models have drastically changed the way humans deal with information. Whereas in the previous century librarians were still classifying books and articles using subject codes, nowadays search technology is available to everyone, everywhere, and in many different contexts. We all use search engines on a daily basis to find relevant information. Not only on the web (e.g. with a search engine or chatGPT), but also in e-commerce websites, social media and news platforms, travel portals, video/music apps, and our email clients. This course covers both the theory and practice of the field of Information Retrieval, with a focus on textual content.
Outline:
Fundamentals:
week 1. Introduction
week 2. Boolean retrieval, indexing and compression
week 3. Evaluation and test collections
Models:
week 4. Vector space model
week 5. Neural IR and Transformers for ranking 1
week 6. Probabilistic IR
week 7 Language Modeling for IR
week 8. Neural IR and Transformers for ranking 2
week 9. (student presentations about critical review of research paper)
Applications:
week 10. Web search and recommender systems
week 11. User interaction and conversational search
week 12. IR in practice (guest lecture)
week 13. IR in the age of LLMs
Course objectives
After successful completion of this course, students are able to:
explain the theoretical underpinnings and implementation of information retrieval models, in particular Boolean retrieval, probabilistic models, vector space models, and transformer models
apply, analyse, and discuss IR models for a given problem setting
explain and apply the common evaluation methods and metrics for IR systems
explain and perform compression algorithms for indexing
list and discuss challenges and models in IR applications, such as web search and conversational search
discuss and evaluate a scientific IR publication
experiment with IR models and evaluate and analyse the outcome
Timetable
The most recent timetable can be found at the Computer Science (MSc) student website.
You will find the timetables for all courses and degree programmes of Leiden University in the tool MyTimetable (login). Any teaching activities that you have sucessfully registered for in MyStudyMap will automatically be displayed in MyTimeTable. Any timetables that you add manually, will be saved and automatically displayed the next time you sign in.
MyTimetable allows you to integrate your timetable with your calendar apps such as Outlook, Google Calendar, Apple Calendar and other calendar apps on your smartphone. Any timetable changes will be automatically synced with your calendar. If you wish, you can also receive an email notification of the change. You can turn notifications on in ‘Settings’ (after login).
For more information, watch the video or go the the 'help-page' in MyTimetable. Please note: Joint Degree students Leiden/Delft have to merge their two different timetables into one. This video explains how to do this.
Mode of instruction
Lectures, homework exercises, literature, assignments (no lab sessions).
Assessment method
The course grade will be computed as follows:
- Homework (weekly exercises, individual) – 10%
- Critical review of a scientific paper (in groups) – 10%
- Practical assignment (in groups) – 20%
- Final written exam (closed book) – 60%
The grade of the homework exercises is based on the number of completed exercises (n_completed/n_total∗10). Because the purpose is exercising, not testing, the homework exercises are not graded, only checked for completion.
Completion of exercises and assignments is not mandatory for passing the course, but the grade for exercises or assignments that are not submitted is 0.
Group work is an integral part of the course. You will be expected to complete the assignments together with a team mate.
The grade for the exam needs to be at least 5.5 to pass the course. The exam has a regular written re-sit opportunity. A weighted average of all components of at least 5.5 is needed to pass the course.
The teacher will inform the students how the inspection of and follow-up discussion of the exams will take place.
Reading list
Both textbooks are publicly available online.
Christopher D. Manning, Hinrich Schütze, and Prabhakar Raghavan (2008): Introduction to information retrieval. Cambridge University Press. ISBN: 978-0521865715 https://nlp.stanford.edu/IR-book/
Jimmy Lin, Rodrigo Nogueira, and Andrew Yates (2021): Pretrained Transformers for Text Ranking: BERT and Beyond. Morgan & Claypool https://arxiv.org/abs/2010.06467
Additional literature will be distributed on Brightspace.
Registration
From the academic year 2022-2023 on every student has to register for courses with the new enrollment tool MyStudyMap. There are two registration periods per year: registration for the fall semester opens in July and registration for the spring semester opens in December. Please see this page for more information.
Please note that it is compulsory to both preregister and confirm your participation for every exam and retake. Not being registered for a course means that you are not allowed to participate in the final exam of the course. Confirming your exam participation is possible until ten days before the exam.
Extensive FAQ's on MyStudymap can be found here.
Contact
Lecturers: