Share This Author
MultiWOZ - A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling
The Multi-Domain Wizard-of-Oz dataset (MultiWOZ), a fully-labeled collection of human-human written conversations spanning over multiple domains and topics is introduced, at a size of 10k dialogues, at least one order of magnitude larger than all previous annotated task-oriented corpora.
A Network-based End-to-End Trainable Task-oriented Dialogue System
This work introduces a neural network-based text-in, text-out end-to-end trainable goal-oriented dialogue system along with a new way of collecting dialogue data based on a novel pipe-lined Wizard-of-Oz framework that can converse with human subjects naturally whilst helping them to accomplish tasks in a restaurant search domain.
Conditional Generation and Snapshot Learning in Neural Dialogue Systems
This work studies various model architectures and different ways to represent and aggregate the source information in an end-to-end neural dialogue system framework to demonstrate competition occurs between the conditioning vector and the LM.
A Parameterized and Annotated Spoken Dialog Corpus of the CMU Let's Go Bus Information System
This work introduces an annotated and standardized corpus in the Spoken Dialog Systems (SDS) domain intended as a standardized basis for classification and evaluation tasks regarding task success prediction, dialog quality estimation or emotion recognition to foster comparability between different approaches on these fields.
PyDial: A Multi-domain Statistical Dialogue System Toolkit
PyDial is an opensource end-to-end statistical spoken dialogue system toolkit which provides implementations of statistical approaches for all dialogue system modules and has been extended to provide multidomain conversational functionality.
Continuously Learning Neural Dialogue Management
A unified neural network framework is proposed to enable the system to first learn by supervision from a set of dialogue data and then continuously improve its behaviour via reinforcement learning, all using gradient-based algorithms on one single model.
On-line Active Reward Learning for Policy Optimisation in Spoken Dialogue Systems
An on-line learning framework whereby the dialogue policy is jointly trained alongside the reward model via active learning with a Gaussian process model is proposed.
Sample-efficient Actor-Critic Reinforcement Learning with Supervised Data for Dialogue Management
- Pei-hao Su, P. Budzianowski, Stefan Ultes, Milica Gasic, S. Young
- Computer ScienceSIGDIAL Conference
- 1 July 2017
A practical approach to learn deep RL-based dialogue policies and demonstrate their effectiveness in a task-oriented information seeking domain is demonstrated.
Interaction Quality: Assessing the quality of ongoing spoken dialog interaction by experts - And how it relates to user satisfaction
Emotions are a personal thing: Towards speaker-adaptive emotion recognition
- M. Sidorov, Stefan Ultes, Alexander Schmitt
- Computer ScienceIEEE International Conference on Acoustics…
- 1 May 2014
Novel work on speech-based adaptive emotion recognition through addition of speaker-specific information is presented, which improves the emotion recognition accuracy by up to +10.2%.