ITI42625 Modern Information Retrieval (Spring 2027)

Recommended pre-knowledge:

• at least 80 ECTS credits in computer science, of which at least 20 ECTS credits in programming.
• basic programming skills
• fundamental knowledge of probability and statistics

Second semester (spring) in the full-time programme.

Fourth semester (spring) in the part-time programme.

The topics covered in this course are:

• A general overview of the field of information retrieval (IR)
• Fundamental principles of indexing, ranking, similarity computation, and evaluation
• Classical retrieval models including vector space models, probabilistic retrieval, and language modeling
• Topic modeling, clustering, and representation learning for exploratory search
• Web-scale IR components such as crawling and link analysis
• Content-based and domain-specific retrieval, including multimedia, time-series and bioinformation retrieval
• LLM-based retrieval techniques, including question answering, prompt/context engineering, and fine-tuning
• Knowledge-integrated retrieval: ontologies, knowledge graphs, and Retrieval-Augmented Generation (RAG)
• Recommendation systems
• Emerging trends in modern IR

Knowledge

The student:

• understands core IR concepts including indexing, ranking models, and evaluation
• knows classical retrieval methods as well as modern neural and LLM-based retrieval techniques, including RAG and knowledge-integrated approaches
• is familiar with major IR application areas such as recommendation systems, topic modeling, and multimedia retrieval

Skills

The student can:

• model real-world problems as retrieval or recommendation tasks and select appropriate representations and algorithms
• implement retrieval pipelines using classical, neural, and LLM-based methods
• evaluate and compare retrieval systems using standard metrics and experimental procedures

General Competence

The student:

• is capable of designing, implementing, and tuning IR systems for diverse data types and application domains
• can integrate indexing, ranking, representation learning, and knowledge sources into functional IR solutions
• can work with modern IR tools, libraries, and frameworks to build end-to-end retrieval applications

The student must deliver:

• Up to 3 mandatory exercises
• Attend one individual oral presentation after submitting the announced exercises

Coursework requirements must be accepted to qualify for the exam.

Individual portfolio and written exam

The exam is divided into two parts:

• The individual portfolio consists of a report and counts for 1/3 of the final grade.
• The individual written exam is based on the course curriculum and counts for 2/3 of the final grade. The duration is 3 hours, and students are allowed to bring one A4 sheet (two pages) of notes.

Both parts must be passed in order to pass the exam as a whole. The student will get an individual joint grade for the entire course. Grades: A - F.

Resit / rescheduled exam is carried out at the same time as the next ordinary examination. The department management can nevertheless decide to arrange a resit exam in the following semester.

Upon re-examination, each part of the examination can be retaken. Upon re-examination, a new project must be carried out.

This course is evaluated by a:

• Final course evaluation

The responsible for the course compiles a report based on the feedback from the students and his/her own experience with the course. The report is discussed by the study quality committee at the Department of Computer Science and Communication.