Keynote

The EMPWR Platform: Data and Knowledge-Driven Processes for the Knowledge Graph Lifecycle

Abstract

The unparalleled volume of generated data has heightened the need for approaches to manage and translate them into decision-making and actionable insights. While contemporary data-driven and GenAI systems are popular for handling large volumes of diverse data, they are stymied due to the lack of grounding or the use of a world model reflecting domain knowledge and facts. Knowledge-driven processes can provide a compelling alternative for leveraging external knowledge and structured representation to complement the shortcomings of contemporary systems. In this keynote, using the example of our EMPWR platform for comprehensive KG development and lifecycle support, I will describe a hybrid approach involving symbolic and GenAI systems to create, combine, align, and maintain large KGs. Specifically, I will showcase the KG development in two real-world use cases: pharmaceuticals and food recommendation (Nutrition KG), involving extracting and integrating knowledge from structured, semi-structured, and unstructured sources and formats. I will illustrate the critical elements and system design guiding principles used to develop EMPWR, its system architectures, and workflow components.  I will conclude by reviewing the current state of AI/NLP and laying out how KG plays a central role in supporting AGI: Alignment, Grounding, and Instructability for a more robust AI.

Speaker Bio:

Prof. Amit Sheth is an Educator, Researcher, and Entrepreneur. He is the NCR Chair & Professor of Computer Sc & Engg, and founded the university-wide AI Institute at the University of South Carolina. He is a Fellow of IEEE, AAAI, AAAS, ACM and AAIA. His awards include IEEE CS W. Wallace McDowell and IEEE TVSVC Research Innovation awards. He has (co-)founded four companies, including the first Semantic Search company in 1999 that pioneered technology similar to what is found today in Google Semantic Search and Knowledge Graph, ezDI, which developed knowledge-infused clinical NLP/NLU, and Cognovi Labs at the intersection of emotion and AI. He is particularly proud of the success of his >>45 Ph.D. advisees and postdocs in academia, industry research, and entrepreneurship.