Next TALC Seminar will take place on Wednesday, January 11th at 2pm in room A008.
Andreas Vlachos (University of Sheffield, UK) will give a presentation entitled “Imitation learning for structure prediction in natural language processing”
Abstract: Imitation learning is a learning paradigm originally developed to learn robotic controllers from demonstrations by humans, e.g. autonomous helicopters from pilot’s demonstrations. Recently, algorithms for structure prediction were proposed under this paradigm and have been applied successfully to a number of tasks such as dependency parsing, information extraction, coreference resolution and semantic parsing. Key advantages are the ability to handle large output search spaces and to learn with non-decomposable loss functions. In this talk I will give a detailed overview of imitation leaning and some recent applications, including its use in training recurrent neural networks.