"Reasoning" can be defined as an ability to derive a new formula (statement) through logical operations on several known formulas, which is a crucial requirement for human-level artificial intelligence. In this talk, I will first argue that natural language, and in particular, question answering, is an effective means of teaching machines to reason and evaluating their performance. Then I will discuss my past approaches to these objectives with regard to three criteria: learning end-to-end, handling syntactic variations, and performing complex inference. I will especially highlight my observation on the strength and the limitation of fully differentiable architectures, such as deep neural networks, for modeling the discrete nature of logic. I will finally conclude with the future direction of my research towards designing the ultimate reasoning machine.

Minjoon Seo is a fourth-year PhD student of Computer Science at the University of Washington, working with Hannaneh Hajishirzi, Ali Farhadi, and Oren Etzioni. He is interested in statistical models for natural language understanding and logical reasoning, with a focus on their application to question answering.