talk: Targeted Knowledge Infusion for AI, 12:15-1:30 2/20

Conversational Systems (CSys) represent practical and tangible outcomes of advances in NLP and AI. CSys see continuous improvements through unsupervised training of large language models (LLMs) on a humongous amount of generic training data. However, when these CSys are suggested for use in domains like Mental Health, they fail to match the acceptable standards of clinical care, such as the clinical process in Patient Health Questionnaire (PHQ-9). The talk will present, Knowledge-infused Learning (KiL), a paradigm within NeuroSymbolic AI that focuses on making machine/deep learning models (i) learn over knowledge-enriched data, (ii) learn to follow guidelines in process-oriented tasks for safe and reasonable generation, and (iii) learn to leverage multiple contexts and stratified knowledge to yield user-level explanations. KiL established Knowledge-Intensive Language Understanding, a set of tasks for assessing safety, explainability, and conceptual flow in CSys.

Manas Gaur is an assistant professor in the Computer Science and Electrical Engineering department at UMBC. Before UMBC, he held the position of Senior AI Research Scientist with the Knowledge and Dialog team within the AI Center at Samsung Research America. He completed his Ph.D. in Computer Science from the Artificial Intelligence Institute at The University of South Carolina. His Ph.D. research was supported by Eric and Wendy Schmidt Data Science for Social Good Fellowship, AI For Social Good Fellowship from Dataminr Inc., EPSRC-UKRI grant through Alan Turing Institute, and NSF-EAGER on Knowledge-infused Learning. His most noted work on Knowledge-infused Learning parallels Neuro-symbolic AI in mental health. His research focuses on knowledge graphs, natural language processing, artificial intelligence, and conversational systems for social good applications.