In this course you will build intelligent systems that are able to interact with their environment through natural language. The fundamental idea behind this is that the meaning of natural language expressions can be modeled as executable programs. For this purpose, we use computational construction grammar, which implements techniques from symbolic AI, including unification, heuristic search, knowledge representation and reasoning.
This course will focus on a specific application, e.g. visual question answering, database querying, robot instructions. A different application is chosen every year, partly depending on the interests of the students. Please note that this course does not deal with text-related NLP, but exclusively targets situated natural language understanding.
It is strongly recommended that you follow the AI Programming Paradigms course, before taking up this course.
The student will acquire the necessary knowledge and skills to manage a challenging AI research project, in the subfield of situated natural language understanding.