Natural Language Generation as Incremental Planning Under Uncertainty: Adaptive Information Presentation for Statistical Dialogue Systems

Abstract

We present and evaluate a novel approach to natural language generation (NLG) in statistical spoken dialogue systems (SDS) using a data-driven statistical optimization framework for incremental information presentation (IP), where there is a trade-off to be solved between presenting "enough" information to the user while keeping the utterances short and understandable. The trained IP model is adaptive to variation from the current generation context (e.g. a user and a non-deterministic sentence planner), and it incrementally adapts the IP policy at the turn level. Reinforcement learning is used to automatically optimize the IP policy with respect to a data-driven objective function. In a case study on presenting restaurant information, we show that an optimized IP strategy trained on Wizard-of-Oz data outperforms a baseline mimicking the wizard behavior in terms of total reward gained. The policy is then also tested with real users, and improves on a conventional hand-coded IP strategy used in a deployed SDS in terms of overall task success. The evaluation found that the trained IP strategy significantly improves dialogue task completion for real users, with up to a 8.2% increase in task success. This methodology also provides new insights into the nature of the IP problem, which has previously been treated as a module following dialogue management with no access to lower-level context features (e.g. from a surface realizer and/or speech synthesizer).

Review of spoken dialogue systems

“…The process of removing such information is called sentence aggregation (Dalianis, 1999). It is possible to find in the literature much more sophisticated and recent approaches than template-based, such as statistical (Dethlefs, Hastie, Cuayáhuitl, & Lemon, 2013;Rieser, Lemon, & Keizer, 2014).…”

A farewell to arms: Non-verbal communication for non-humanoid robots

“…Previous work has explored the problem of adapting the form and content of generated utterances to situational constraints (e.g. Jokinen and Wilcock, 2003;Walker et al, 2007;Rieser et al, 2014), but typically not in the context of human-robot interaction. In order to illustrate our position, we will describe some results and observations from our ongoing research on making human-robot communication more robust using non-verbal signals.…”

Proceedings of the Workshop on NLG for Human–Robot Interaction

“…Previous work has explored the problem of adapting the form and content of generated utterances to situational constraints (e.g. Jokinen and Wilcock, 2003;Walker et al, 2007;Rieser et al, 2014), but typically not in the context of human-robot interaction.…”