Large language models like ChatGPT have shown extraordinary abilities for writing. While impressive at first glance, large language models aren't perfect and often make mistakes humans would not make. The main architecture behind ChatGPT mostly doesn't differ from early neural networks, and as a consequence, carries some of the same limitations. In this talk, I discuss the use of neural networks like ChatGPT combined with symbolic methods from early AI and how combining the two families of methods can yield more robust AI. In particular, I talk about some of the neurosymbolic methods I used for applications in story generation and understanding -- with the goal of eventually creating AI that can play Dungeons & Dragons.
Dr. Lara J. Martin is an assistant professor at the University of Maryland, Baltimore County in the Computer Science & Electrical Engineering department. Prior to her current appointment, Dr. Martin was a 2020 Computing Innovation Fellow (CIFellow) postdoctoral researcher at the University of Pennsylvania. In 2020, she earned her PhD in Human-Centered Computing from the Georgia Institute of Technology, where she did her dissertation on Neurosymbolic Automated Story Generation. They also have a Masters of Language Technologies from Carnegie Mellon University and a BS in Computer Science & Linguistics from Rutgers University—New Brunswick. Dr. Martin’s work resides in the field of Human-Centered Artificial Intelligence with a focus on natural language applications. In addition to story generation, they have worked in the areas of accessible technologies, speech processing, and affective computing, publishing in top-tier conferences such as AAAI and IJCAI. They have been featured in Wired, BBC Science Focus magazine, and The Register.