Abstract
In task-oriented dialogues, there is often only one right answer the system can give. However, a lack of variation can seem repetitive and unnatural. Humans change the way they express something, e.g. by being more or less concise. We aim to approximate this ability by automatically varying the level of verbosity and directness of a given system action. In this work, we illustrate how verbosity and directness may be utilised in adaptive dialogue management and present different approaches to automatically generate varying levels of verbosity and directness for given system actions. Thereby, new and unforeseen system actions can be created dynamically.
Cite
CITATION STYLE
Pragst, L., Miehle, J., Ultes, S., & Minker, W. (2016). Automatic modification of communication style in dialogue management. In CC-NLG 2016 - INLG 2016 Workshop on Computational Creativity in Natural Language Generation, Proceedings (pp. 36–40). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/W16-5506
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.