Optimising Natural Language Generation Decision Making For Situated Dialogue

Nina Dethlefs1,  Heriberto CuayĆ”huitl2,  Jette Viethen3
1University of Bremen, 2German Research Centre for Artificial Intelligence, 3Macquarie University


Natural language generators are faced with a multitude of different decisions during their generation process. We address the joint optimisation of navigation strategies and referring expressions in a situated setting with respect to task success and human-likeness. To this end, we present a novel, comprehensive framework that combines supervised learning, Hierarchical Reinforcement Learning and a hierarchical Information State. A human evaluation shows that our learnt instructions are rated similar to human instructions, and significantly better than the supervised learning baseline.