Effective, Explainable, and Equitable NLP with World Knowledge and Interactions

Explore the intersection of artificial intelligence and natural language processing in this informative talk by Bodhisattwa Prasad Majumder from UCSD. Delve into the challenges of creating AI systems that are not only effective but also explainable, equitable, and grounded in world knowledge. Learn about innovative approaches to inject relevant knowledge into dialog models, investigate the role of background knowledge in model reasoning, and address fairness through interactive bias mitigation. Gain insights into the future possibilities and societal impacts of explainable interactive systems. Discover how this research aims to bridge the gap between current AI capabilities and the growing expectations for trust, accessibility, and anthropomorphism in knowledge-seeking applications.