Question Answering: Deep Learning Insights

This lecture delves into the realm of question answering, aiming to build systems that automatically respond to queries in natural language. Starting from the earliest QA systems in the 1960s, the lecture explores the taxonomy of question answering, including information sources, question types, and answer formats. Practical applications like Google search are highlighted, showcasing the importance of QA systems. The lecture further discusses reading comprehension, where systems are designed to understand text passages and answer questions about them. Various models such as BiDAF and BERT are compared, shedding light on their performance on datasets like SQUAD. The lecture concludes by addressing the challenges in reading comprehension, emphasizing the need for robust systems that can handle adversarial examples and out-of-domain distributions.