Paper: Natural Language Generation as Planning Under Uncertainty for Spoken Dialogue Systems

ACL ID E09-1078
Title Natural Language Generation as Planning Under Uncertainty for Spoken Dialogue Systems
Venue Annual Meeting of The European Chapter of The Association of Computational Linguistics
Session Main Conference
Year 2009
Authors

We present and evaluate a new model for Natural Language Generation (NLG) in SpokenDialogueSystems, basedonstatis- tical planning, given noisy feedback from the current generation context (e.g. a user and a surface realiser). We study its use in a standard NLG problem: how to present information (in this case a set of search re- sults) to users, given the complex trade- offs between utterance length, amount of information conveyed, and cognitive load. We set these trade-offs by analysing exist- ing MATCH data. WethentrainaNLGpol- icy using Reinforcement Learning (RL), which adapts its behaviour to noisy feed- back from the current generation context. This policy is compared to several base- lines derived from previous work in this area. The learned policy significantly out- performs all th...