Optimising Natural Language Generation Decision Making For Situated Dialogue

Nina Dethlefs, Dr. Heriberto Cuayáhuitl

In: Proceedings of the Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL). Annual SIGdial Meeting on Discourse and Dialogue (SIGdial-2011) 12th June 17-18 Portland Oregon United States Seiten 78-87 ISBN 978-1-937284-10-7 ACL 7/2011.


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.


hc-sigdial2011.pdf (pdf, 470 KB )

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence