Technical Programme

This is the final programme for this session. For oral sessions, the timing on the left is the current presentation order, but this may still change, so please check at the conference itself. If you have signed in to My Schedule, you can add papers to your own personalised list.

Wed-Ses3-S1:
Special Session: Machine Learning for Adaptivity in Spoken Dialogue Systems

Time:	Wednesday 16:00	Place:	East Wing 4	Type:	Special
Chair:	Oliver Lemon & Olivier Pietquin

16:00	A User Modeling-based Performance Analysis of a Wizarded Uncertainty-Adaptive Dialogue System Corpus Kate Forbes-Riley (Learning Research and Development Center (LRDC), University of Pittsburgh, USA) Diane Litman (Learning Research and Development Center (LRDC), University of Pittsburgh, USA) Motivated by prior spoken dialogue system research in user modeling, we analyze interactions between performance and user class in a dataset previously collected with two wizarded spoken dialogue tutoring systems that adapt to user uncertainty. We focus on user classes defined by expertise level and gender, and on both objective (learning) and subjective (user satisfaction) performance metrics. We find that lower expertise users learn best from one adaptive system but prefer the other, while higher expertise users learned more from one adaptive system but didn’t prefer either. Female users both learn best from and prefer the same adaptive system, while males preferred one adaptive system but didn’t learn more from either. Our results yield an empirical basis for future investigations into whether adaptive system performance can improve by adapting to user uncertainty differently based on user class.
16:20	Using Dialogue-Based Dynamic Language Models for Improving Speech Recognition Juan Manuel Lucas-Cuesta (Speech Technology Group, Universidad Politécnica de Madrid) Fernando Fernández-Martínez (Speech Technology Group, Universidad Politécnica de Madrid) Javier Ferreiros (Speech Technology Group, Universidad Politécnica de Madrid) We present a new approach to dynamically create and manage different language models to be used on a spoken dialogue system. We apply an interpolation based approach, using several measures obtained by the Dialogue Manager to decide what LM the system will interpolate and also to estimate the interpolation weights. We propose to use not only semantic information (the concepts extracted from each recognized utterance), but also information obtained by the dialogue manager module (DM), that is, the objectives or goals the user wants to fulfill, and the proper classification of those concepts according to the inferred goals. The experiments we have carried out show improvements over word error rate when using the parsed concepts and the inferred goals from a speech utterance for rescoring the same utterance.
16:40	Reinforcement Learning for Dialog Management using Least-Squares Policy Iteration and Fast Feature Selection Lihong Li (Rutgers University) Jason Williams (AT&T Labs - Research) Suhrid Balakrishnan (AT&T Labs - Research) Reinforcement learning (RL) is a promising technique for creating a dialog manager. RL accepts features of the current dialog state and seeks to find the best action given those features. Although it is often easy to posit a large set of potentially useful features, in practice, it is difficult to find the subset which is large enough to contain useful information yet compact enough to reliably learn a good policy. In this paper, we propose a method for RL optimization which automatically performs feature selection. The algorithm is based on least-squares policy iteration, a state-of-the-art RL algorithm which is highly sample-efficient and can learn from a static corpus or on-line. Experiments in dialog simulation show it is more stable than a baseline RL algorithm taken from a working dialog system.
17:00	Hybridisation of Expertise and Reinforcement Learning in Dialogue Systems Romain Laroche (Orange Labs & LIP6) Ghislain Putois (Orange Labs) Philippe Bretier (Orange Labs) Bernadette Bouchon-Meunier (LIP6 & CNRS) This paper addresses the problem of introducing learning capabilities in industrial handcrafted automata-based Spoken Dialogue Systems, in order to help the developer to cope with his dialogue strategies design tasks. While classical reinforcement learning algorithms position their learning at the dialogue move level, the fundamental idea behind our approach is to learn at a finer internal decision level (which question, which words, which prosody, \dots). These internal decisions are made on the basis of different (distinct or overlapping) knowledge. This paper proposes a novel reinforcement learning algorithm that can be used to make a data-driven optimisation of such handcrafted systems. An experiment shows that the convergence can be up to 20 times faster than with Q-Learning.
17:20	Bayesian Learning of Confidence Measure Function for Generation of Utterances and Motions in Object Manipulation Dialogue Task Komei Sugiura (National Institute of Information and Communications Technology) Naoto Iwahashi (National Institute of Information and Communications Technology) Hideki Kashioka (National Institute of Information and Communications Technology) Satoshi Nakamura (National Institute of Information and Communications Technology) This paper proposes a method that generates motions and utterances in an object manipulation dialogue task. The proposed method integrates belief modules for speech, vision, and motions into a probabilistic framework so that a user's utterances can be understood based on multimodal information. Responses to the utterances are optimized based on an integrated confidence measure function for the integrated belief modules. Bayesian logistic regression is used for the learning of the confidence measure function. The experimental results revealed that the proposed method reduced the failure rate from 12% down to 2.6% while the rejection rate was less than 24%.
17:40	Predicting how it sounds: Re-ranking dialogue prompts based on TTS quality for adaptive Spoken Dialogue Systems Cedric Boidin (Orange Labs) Verena Rieser (University of Edinburgh) Lonneke van der Plas (University of Geneva) Oliver Lemon (University of Edinburgh) Jonathan Chevelu (Orange Labs) This paper presents a method for adaptively re-ranking paraphrases in a Spoken Dialogue System (SDS) according to their predicted Text To Speech (TTS) quality. We collect data under 4 different conditions and extract a rich feature set of 55 TTS runtime features. We build predictive models of user ratings using linear regression with latent variables. We then show that these models transfer to a more specific target domain on a separate test set. All our models significantly outperform a random baseline. Our best performing model reaches the same performance as reported by previous work, but it requires 75% less annotated training data. The TTS re-ranking model is part of an end-to-end statistical architecture for Spoken Dialogue Systems developed by the CLASSiC project.