Description:

This lecture provides in-depth knowledge in the field of Information Retrieval (IR) - the science of searching, finding and understanding relevant information in large amounts of data, especially on the web. The course ranges from the technical basics of web technologies to classical IR methods and modern developments such as Large Language Models (LLMs) and semantic knowledge graphs.

Topic overview:

• Introduction to Information Retrieval: Motivation, fields of application and basic concepts.
• Web technologies: HTTP, REST, HTML and CSS as the basis for web data access and presentation.
• Web Crawling & Scraping: Methods for the automated collection and extraction of web content.
• Natural Language Processing (NLP): Processing of natural language to improve search quality.
• Large Language Models (LLMs): Fundamentals, architecture and application of large pre-trained language models.
• Knowledge graphs and semantic search: Structured knowledge representation for more precise information queries.

Aims of the event:

Participants will learn how modern search systems work, which technologies enable them and how current AI methods such as LLMs are used in this context. In addition to theoretical knowledge, a special focus is placed on practical applications and current research trends.

Prerequisites:

Basic knowledge of programming and web technologies is helpful, but not essential. The course is also open to non-specialists with an interest in technology.