Graph Power Hour Ep 9
The Mighty Thesaurus:
Leveraging Library Science
in Building AI Systems
Webinar Series with Paco Nathan of Senzing & Guest Jessica Talisman
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.
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 domainโspecific 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.
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.
Helpful Links:
Knowledge Graph Lite Article Series:
Part I: https://jessicatalisman.substack.com/p/knowledge-graph-lite?r=ee6qm
Part II: https://jessicatalisman.substack.com/p/knowledge-graph-lite-part-ii?r=ee6qm
Part III: https://jessicatalisman.substack.com/p/knowledge-graph-lite-part-iii?r=ee6qm
Additional Resources:
We’d love to see you at our next event! Keep an eye out for our upcoming webinars by subscribing to our mailing list and following Senzing on LinkedIn.
Related Videos
Paco Nathan
Principal DevRel Engineer
Paco Nathan leads DevRel for the Entity Resolved Knowledge Graph practice area at Senzing and is a computer scientist with +40 years of tech industry experience and core expertise in data science, natural language, graph technologies, and cloud computing. He’s the author of numerous books, videos, and tutorials about these topics.
Jessica Talisman
Senior Information Architect, Adobe
Jessica Talisman is an information architect and semantic technologist with 25+ years designing semantic architectures across enterprise tech and cultural institutions. A formerly trained librarian and information scientist, Jessica works at the intersections of culture and technology. Former roles include Senior Information Architect at Adobe, Information Architect at Amazon, and positions at Pluralsight, GDIT, Overstock.com, and the Department of Justice. She created the Ontology Pipelineโข framework, to help organizations build coherent data ecosystems. Through consulting, courses, and interdisciplinary dialogue, Jessica seeks to advance collaboration between people, machines, and systems.
