Abstract

Abstract: In this talk I present a novel approach to Natural Language Generation (NLG) in statistical Spoken Dialogue Systems, e.g. [Williams & Young, 2007], using a data-driven statistical optimisation 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. In a case study on recommending restaurants, we show that an optimised IP strategy outperforms a baseline mimicking human behaviour in terms of total reward gained, in simulation. The policy is then also tested with real users, and improves on a conventional hand-coded IP strategy with up to a 9.7% increase in task success. This methodology provides new insights into the nature of the NLG problem, which has previously been treated as a module following dialogue management with limited access to context features. This type of model is now widely used in research applications, which I will briefly discuss. For example, optimising information presentation in recommender systems [Rieser & Lemon, 2010], hierarchical NLG [Dethlefs and Cuaya ́huitl 2011], personalisation [Janarthanam and Lemon 2010; Janarthanam et al. 2011] and efficient incremental search [Dethlefs et al. 2012b; 2012a] and trading agents [Rieser et al. 2012].

Short Bio: Verena is a lecturer in Computer Science at Heriot-Watt University, Edinburgh. Before she has undertaken post-doctoral research at the Schools of Informatics and GeoSciences at the University of Edinburgh. She holds a PhD (summa cum laude) from Saarland University (2008) and an MSc with distinction from the University of Edinburgh (2004). Her PhD also received the Dr. Eduard-Martin award for distinguished doctoral dissertations. Her research is at the intersection of Machine Learning and Natural Language Processing, with applications ranging from Multi-Modal Interaction, Spoken Dialogue System and Computational Sustainability. She is currently serving as secretary for the ACL Special Interest group in Natural Language Generation (SIGGEN) and she has recently published a book on “Reinforcement Learning for Spoken Dialogue Systems” (Springer, 2011). Since starting her research career in 2005, she has co-authored over 40 original research papers, which were cited over 400 times (H-Index: 13 according to Google Scholar). Verena has strong ties to industry, where she is a visiting researcher at Nuance’s Research Lab, Sunnyvale in 2013. For more details please see: http://www.macs.hw.ac.uk/~vtr1/