This information sheet indicates how the course will be organized at pandemic code level yellow and green.
If the colour codes change during the academic year to orange or red, modifications are possible, for example to the teaching and evaluation methods.

Information retrieval

Course Code :2001WETINR
Study domain:Computer Science
Academic year:2020-2021
Semester:1st semester
Contact hours:60
Credits:6
Study load (hours):168
Contract restrictions: No contract restriction
Language of instruction:English
Exam period:exam in the 1st semester
Lecturer(s)Toon Calders

3. Course contents *

The course covers the foundations of current ranking techniques (which are often based on statistical models), index structures, and current implementation issues for the design of effective and scalable information-system architectures. The course covers a wide range of ranking principles, starting from the Boolean retrieval model, over to statistical ranking models such as TF-IDF, and on to probabilistic ranking techniques such as Okapi-BM25. The course will cover classical IR topics, including link-analysis methods such as PageRank, the user-specific personalization of queries, and relevance feedback. 

The course topics are:

 

  • Boolean retrieval
  • Vector Space Model
  • Language Based Model
  • Boolean Independence Model
  • Top-K querying and Index construction
  • Index construction and compression
  • Feedback-Expansion
  • Evaluating IR
  • Link analysis
  • Dimensionality Reduction
  • Neighbor search in high dimensional data