Thursday, 25 June 2026
| 12:45 | Join in |
| 13:00 | Welcome, Motivation & Introduction |
| 13:05 | Introduction to Natural Language Processing for Information Extraction |
| Overview of natural language processing tasks with a focus on information extraction. Explanation of what entities, relations, and facts are, and how structured knowledge can be derived from unstructured text. Typical application scenarios and limitations. | |
| 13:20 | Methods for Entity Recognition and Information Extraction |
| Overview of different methodological approaches for information extraction. Comparison of strengths, weaknesses, and suitable use cases | |
| – Simple pattern-based methods (e.g. regular expressions and rules) | |
| – Classical machine learning and sequence learning approaches for entity recognition | |
| – Modern approaches using general purpose models and Retrieval-Augmented Generation (RAG) | |
| 13:45 | Break |
| 13:55 | Hands-On Session: End-to-end programming exercise in Jupyter Notebooks |
| – Exploring and preprocessing unstructured text data | |
| – Applying simple rule-based extraction approaches | |
| – Performing named entity recognition and text classification using machine learning models | |
| – Experimenting with embedding-based methods and semantic search | |
| – Using large language models for information extraction and enrichment | |
| – Inspecting, validating, and interpreting results | |
| 16:00 | End of course |
