Explore the challenges and advancements in answering "why" questions about narrative text in this informative lecture by Ray Mooney from the University of Texas, Austin. Delve into the TellMeWhy corpus, a crowd-sourced dataset of over 30,000 questions and answers about character motivations in short narratives. Examine the limitations of current models in answering such questions and learn about novel evaluation methods developed for this task. Discover how large language models and external commonsense knowledge resources contribute to improving performance in why-question answering. Gain insights into the strengths and weaknesses of current approaches, including instances where models outperform human answers and areas where significant improvements are still needed.