Neural Information Retrieval (NIR)
The course objective is to offer an advanced introduction into information retrieval. The goal is to understand and model how people search for, access and use information, in order to design and evaluate reliable retrieval algorithms. Through realistic and sound projects, the course aims to stimulate and prepare students for their MSc thesis work.
The course will focus on these main questions:
- How can we design efficient retrieval systems?
- How can we design effective retrieval systems?
Content in detail:
Architecture of an IR system
- Basic building blocks
- Crawling, filtering and storing information
- Ranking with indexes
Information ranking models
- Deep learning for search engines
- Probabilistic & machine learning models
- Complex queries and combining evidence
- Domain-specific ranking
- Evaluation and optimisation
MSc Programme in Computer Science
- The basic architecture of retrieval systems
- The basic models and techniques for collecting, storing and ranking information
- Different criteria for information retrieval evaluation
Students should be able to transfer the above knowledge to real-world tasks by:
- Designing appropriate strategies for crawling, storing and ranking information
- Planning and carrying out appropriate evaluations
Given a working retrieval system, students should be able to:
- Diagnose problems in its main information processing functions
- Design and calibrate appropriate solutions
- Explain the basic information retrieval principles to both laymen and specialists
- Use standard procedures and practices when designing or implementing information retrieval solutions
- Present evaluation analyses and results in a proper format of a written report such that a technically qualified person can follow and obtain similar findings
The course will use a combination of lectures (2 hours per week)
and lab sessions (2 hours per week). Lectures and labs might
include discussions, group activities, and student presentations.
Where possible, relevant guest lecturers will be involved.
Students will carry-out a project which consists of both practical exercises (implementing state of the art solutions) and theoretical questions (to reflect on the course content in relation to the project). The project will cover the main topics presented during the lectures.
The literature consists of seminal research and review articles
from central journals and selected papers from peer-reviewed
conferences, textbooks and research reports. This is supplemented
with practical experience gained through lab sessions.
The literature will be listed in Absalon.
It is expected that students know how to program and have a
working knowledge of Machine Learning corresponding to the course
Machine Learning (ML) or an equivalent course.
Academic qualifications equivalent to a BSc degree is recommended.
The course is identical to NDAK15005U Information Retrieval
It is not allowed to pass both courses.
PhD’s can register for MSc-course by following the same procedure as credit-students, see link above.
- 7,5 ECTS
- Type of assessment
Written assignmentOral examination, 20 min
- Type of assessment details
- Specifically, the exam consists of two parts:
1. An individual report (written assignment) based on the project.
2. An individual oral examination (without preparation) based on the report.
The written and oral examination are not weighted, why only one overall assessment is provided for the two parts of the exam.
- All aids allowed
- Marking scale
- 7-point grading scale
- Censorship form
- No external censorship
Several internal examiners
Criteria for exam assessment
See Learning Outcome.
Single subject courses (day)
- Project work
- Exam Preparation
- Course number
- 7,5 ECTS
- Programme level
- Full Degree Master
- Block 4
- No limit
The number of seats may be reduced in the late registration period
- Study Board of Mathematics and Computer Science
- Department of Computer Science
- Faculty of Science
- Christina Lioma (7-6934726f757367466a6f34717b346a71)
Are you BA- or KA-student?
Courseinformation of students