Overview

As AI-driven language interfaces (such as chat-bots) become more integrated into our lives, they need to become more versatile and reliable in their communication with human users. What technologies are behind such developments and what are the open challenges? In this talk, I will describe the recent advances in natural language processing, particularly the advent of language models and the different ways it has affected the state of our technology. Then I will focus on the open problems that we are facing. I will conclude with my speculations on the future of NLP research toward broader NLP systems by addressing the limitations of the presented ideas and other missing elements needed to move toward more general-purpose interactive language understanding systems.