Tell Me Why I Need A Thesaurus

Jessica Talisman has been publishing a series of articles on Substack about how to develop more robust AI systems by leveraging vocabularies, thesauri, taxonomies, and ontologies -- leveraging context as an intentional arrangement of domain–specific knowledge.

As people throughout the tech industry are recognizing crucial needs for robust context engineering practices, Jessica has been busy reminding us that people have been cataloging information for the past 3000 years or so, in ways which evolved steadily as technology advanced.

Library and Information Science as a discipline builds systems for organizing data based on the practice of intentional arrangement, which we can leverage for better knowledge graph practices and more robust AI applications downstream.

In this episode of "Graph Power Hour!", Jessica Talisman will guide us through the basics of using a thesaurus and shared vocabularies for fact-setting in particular, and leveraging Library Science as preparation for building AI Systems in general. To borrow a quote from Alessandro Negro, this is the process of "Crafting knowledge for humans and machines alike." While a thesaurus is important for information retrieval and discovery systems -- with or without AI -- a thesaurus is also a mighty workhorse for the symbolic side of AI approaches, aka working with knowledge graphs. Jessica will present about the concept of a thesaurus as a foundational framework for all AI use cases.

Spoiler alert: running Senzing entity resolution on your structured datasets produces a domain-specific thesaurus. This can be leveraged for knowledge graph construction, entity linking, semantic search beyond what either graph queries or vector databases provide, and much more.