Knowledge graph construction

Welcome to Knowledge graph construction

Description: The ability to represent and reason with knowledge in a structured, machine-readable format is rapidly becoming essential for modern artificial intelligence applications. Knowledge graphs (KGs) offer a powerful paradigm for achieving this, enabling applications ranging from intelligent search and question answering to drug discovery and personalized medicine. However, constructing high-quality KGs is a complex undertaking, requiring expertise in information extraction, entity resolution, and data integration – challenges that lie at the intersection of knowledge engineering, information retrieval, natural language processing, and increasingly, domain-specific knowledge.
This course addresses the problem of building robust knowledge graphs from diverse data sources. The course will start with a comprehensive introduction to the principles and techniques underlying KG construction, starting from the basic KG concepts, (e.g. data models and query languages), and continuing with advanced topics such as information extraction from free text, entity matching, and KG ingestion. The course will also discuss approaches based on large language models (LLMs) for automating the extraction of structured data from text. As a use-case to illustrate the application of the notions and techniques, the course will consider real-world applications within the medical domain.

Prerequisites: Familiarity with Python

Learning objectives: 

On successful completion of this course, students will be expected to be able to:

1. Develop a good understanding of knowledge graphs (KGs), their significance in representing and reasoning with structured information, and the diverse applications where they are utilized.
2. Design, implement, and evaluate workflows for constructing knowledge graphs from diverse data sources, including free text and structured databases. This includes core techniques for information extraction, entity resolution, named entity recognition and KG ingestion.
3. Critically assess and compare different approaches to knowledge graph construction, including traditional methods and contemporary techniques leveraging LLMs.
4. Apply knowledge graph techniques to a real-world problem, demonstrating an ability to design, implement, and evaluate a complete knowledge graph solution.

Organizer: Daniele Dell'Aglio

Lecturers: Daniele Dell'Aglio and Gianmaria Silvello

ECTS: 2

Time: 28 and 29 May 2026

Place: Aalborg University

City: Aalborg

Maximal number of participants: 30

Deadline: 07 May 2026

Important information concerning PhD courses: 

There is a no-show fee of DKK 3,000 for each course where the student does not show up. Cancellations are accepted no later than 2 weeks before the start of the course. Registered illness is of course an acceptable reason for not showing up on those days. Furthermore, all courses open for registration approximately four months before start of the course.

We cannot ensure any seats before the deadline for enrolment, all participants will be informed after the deadline, approximately 3 weeks before the start of the course.

For inquiries regarding registration, cancellation or waiting list, please contact the PhD administration at phdcourses@adm.aau.dk When contacting us please state the course title and course period. Thank you.