Seminars and Events

Artificial Intelligence Seminar

From NLP to NLU: Why we need varied, comprehensive, and stratified knowledge, and how to use it for Neuro-symbolic AI

Event Details

“Data alone is not enough.” This was the section heading in Pedro Domingos’ 2012 seminal paper. In the first commercial Semantic Search engine deployed in 2000, we complemented machine learning classifiers with a comprehensive WorldModel(™) or knowledge bases (now referred to as knowledge graphs) for improved named entity and relationship extraction and semantic search (details in this paper). It was an early demonstration of the complementary nature of data-driven statistical learning (now neural networks) and knowledge-supported symbolic AI methods, which was explored in 2005 “Informal (machine learning), Formal (symbolic), and Power semantics” paper.  While the transformer-based models have achieved tremendous success in many NLP tasks, the pure data-driven approach comes up short when we need NLU, where knowledge is key to understanding the language, as required for the explanation, safety, and supporting decision-making processes.


In this talk, I discuss the importance of using knowledge to address several challenges ChatGPT/GenerativeAI systems face, such as hallucinations, lack of recency (recent content, facts, and knowledge), lack of user-level explainability, and lack of application-level safety, and about addressing these in knowledge-enhanced neuro-symbolic AI systems. I discuss (a) why: understanding is only possible with the use of relevant knowledge, (b) what: the knowledge needed to support more demanding activities is multifaceted and comprehensive; it needs to cover multiple levels of abstraction. For example, humans utilize all these types of knowledge to understand a natural language: lexical, linguistic, common sense including a sense of time, geographic and sense of location, broad-based or world knowledge, domain/subject/task-specific knowledge, and process knowledge (i.e., technical-organizational measures such as clinical practice guidelines, human decision-makers must follow), and (c) how: various ways of (shallow, semi-deep, and deep) knowledge-infusion and knowledge-elicitation to use neural network and symbolic components synergistically. For background, see: Advancing Neuro-symbolic AI with Deep Knowledge-infused Learning.

Speaker Bio

Prof. Amit Sheth (Home Page, LinkedIn) is an Educator, Researcher, and Entrepreneur. He is the founding director of the university-wide AI Institute, NCR Chair & Professor of Computer Sc & Engg at the University of South Carolina. He is a Fellow of IEEE, AAAI, AAAS and ACM. His awards include IEEE CS Wallace McDowell Award and IEEE TCSVC Research Innovation award. 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 entrepreneurs.

YOU ONLY NEED TO REGISTER ONCE TO ATTEND THE ENTIRE SERIES – We will send you email announcements with details of the upcoming speakers.

Register in advance for this webinar:

After registering, you will receive an email confirmation containing information about joining the Zoom webinar.

The speaker approved to be recorded for this AI Seminar talk; it will be posted on our USC/ISI YouTube page within 1-2 business days:

Host: Mohammad Rostami POC: Alma Nava