Automated Metadata Extraction with Annif and BIBRA

Libraries and other organizations are adopting and investigating automated techniques for generating metadata; the role of AI is ever increasing in workflows. This course provides an overview and demonstration of the open-source multilingual automated indexing tool Annif, which can be incorporated, e.g., into a library’s metadata creation and management system. We will work on a new solution for automated bibliographic metadata extraction, BIBRA, which will be presented and demonstrated here. We will evaluate and discuss the quality and use of automatically generated metadata. Additionally, the existing Annif tutorial material will be introduced to allow participants to continue further exploration with the tool.

Learning Objectives

By the end of this course, participants will be able to:

1. Describe the capabilities and practical applications of open-source tools to perform metadata extraction.
2. Evaluate the quality and practical utility of automatically generated metadata in systems.

Schedule