Chapter

Empirical Methods in Natural Language Generation

Volume 5790 of the series Lecture Notes in Computer Science pp 105-120

Natural Language Generation as Planning under Uncertainty for Spoken Dialogue Systems

  • Verena RieserAffiliated withCarnegie Mellon UniversitySchool of Informatics, University of Edinburgh
  • , Oliver LemonAffiliated withCarnegie Mellon UniversitySchool of Mathematical and Computer Sciences, Heriot-Watt University

* Final gross prices may vary according to local VAT.

Get Access

Abstract

We present and evaluate a new model for Natural Language Generation (NLG) in Spoken Dialogue Systems, based on statistical planning, given noisy feedback from the current generation context (e.g. a user and a surface realiser). The model is adaptive and incremental at the turn level, and optimises NLG actions with respect to a data-driven objective function. We study its use in a standard NLG problem: how to present information (in this case a set of search results) to users, given the complex trade-offs between utterance length, amount of information conveyed, and cognitive load. We set these trade-offs in an objective function by analysing existing match data. We then train a NLG policy using Reinforcement Learning (RL), which adapts its behaviour to noisy feedback from the current generation context. This policy is compared to several baselines derived from previous work in this area. The learned policy significantly outperforms all the prior approaches.

Keywords

Reinforcement Learning Adaptivity Spoken Dialogue Systems Information Presentation Incremental NLG Optimisation data-driven methods