Statistical approaches to dialogue management have brought improvements in robustness and scalability of spoken dialogue systems, but still rely heavily on in-domain data, thus limiting their cross-domain scalability. In this paper, we present a new multi-dimensional, statistical dialogue management framework, in which transferable conversational skills can be learnt by separating out domain-independent dimensions of communication. Our preliminary experiments demonstrate the effectiveness of such transfer.
Cite as: Keizer, S., Rieser, V. (2017) Towards Learning Transferable Conversational Skills using Multi-dimensional Dialogue Modelling. Proc. SEMDIAL 2017 (SaarDial) Workshop on the Semantics and Pragmatics of Dialogue, 150-151.
@inproceedings{Keizer2017,
author={Simon Keizer and Verena Rieser},
title={Towards Learning Transferable Conversational Skills using Multi-dimensional Dialogue Modelling},
year=2017,
booktitle={Proc. SEMDIAL 2017 (SaarDial) Workshop on the Semantics and Pragmatics of Dialogue},
pages={150--151}
}