Information Retrieval 2

Course manual 2025/2026

Course content

Building on the Information Retrieval 1 course (MSc AI, 1st year), but also pivoting on Natural Language Processing, Machine Learning and Deep Learning, this course will focus on the design, execution, and analysis of state-of-the-art retrieval methods.

Recent years has seen the rise of neural networks approximating complex models of the past, such as the generation and understanding of language. At the same time Human-Computer Interaction has progressed in ways such that modern interface are screen-less and voice-based. Information seeking require machines not only to analyze and understand human language, but also initiate a conversation with humans to better locate the information they seek. 

Study materials

Other

• Recent literature.

Objectives

• The student can explain the latest research on information retrieval, large language models, question answering, and conversational search
• The student can apply neural models, in the domain of retrieval, question answering, and conversational search
• The student can evaluate IR models using existing benchmarks
• The student can create novel models and methods for retrieval, question answering, and conversational search
• The student can reproduce the most recent research outcomes in information retrieval and generalize the experiments in new environments

Teaching methods

Project-based, with weekly meetings, with active student participation and contributions. Mid-term status update. Final presentation.

Learning activities

Attendance

This programme does not have requirements concerning attendance (OER part B).

Assessment

Fraud and plagiarism

The 'Regulations governing fraud and plagiarism for UvA students' applies to this course. This will be monitored carefully. Upon suspicion of fraud or plagiarism the Examinations Board of the programme will be informed. For the 'Regulations governing fraud and plagiarism for UvA students' see: www.student.uva.nl

Course structure

Additional information

Maximum number of students: 25

Recommended prior knowledge: Information retrieval 1, machine learning 1

Contact information

Coordinator

• dr. Mohammad Alian Nejadi