Stefan Ultes
Stefan Ultes
Dialogue Research Lead, Mercedes Benz R&D
Verified email at - Homepage
Cited by
Cited by
A network-based end-to-end trainable task-oriented dialogue system
TH Wen, D Vandyke, N Mrksic, M Gasic, LM Rojas-Barahona, PH Su, ...
arXiv preprint arXiv:1604.04562, 2016
MultiWOZ--A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling
P Budzianowski, TH Wen, BH Tseng, I Casanueva, S Ultes, O Ramadan, ...
arXiv preprint arXiv:1810.00278, 2018
On-line active reward learning for policy optimisation in spoken dialogue systems
PH Su, M Gasic, N Mrksic, L Rojas-Barahona, S Ultes, D Vandyke, ...
arXiv preprint arXiv:1605.07669, 2016
Pydial: A multi-domain statistical dialogue system toolkit
S Ultes, LMR Barahona, PH Su, D Vandyke, D Kim, I Casanueva, ...
Proceedings of ACL 2017, System Demonstrations, 73-78, 2017
Continuously learning neural dialogue management
PH Su, M Gasic, N Mrksic, L Rojas-Barahona, S Ultes, D Vandyke, ...
arXiv preprint arXiv:1606.02689, 2016
Sample-efficient actor-critic reinforcement learning with supervised data for dialogue management
PH Su, P Budzianowski, S Ultes, M Gasic, S Young
arXiv preprint arXiv:1707.00130, 2017
A parameterized and annotated spoken dialog corpus of the cmu let’s go bus information system
A Schmitt, S Ultes, W Minker
International Conference on Language Resources and Evaluation (LREC), 2012
Conditional generation and snapshot learning in neural dialogue systems
TH Wen, M Gasic, N Mrksic, LM Rojas-Barahona, PH Su, S Ultes, ...
arXiv preprint arXiv:1606.03352, 2016
Interaction quality: assessing the quality of ongoing spoken dialog interaction by experts—and how it relates to user satisfaction
A Schmitt, S Ultes
Speech Communication 74, 12-36, 2015
A benchmarking environment for reinforcement learning based task oriented dialogue management
I Casanueva, P Budzianowski, PH Su, N Mrkšić, TH Wen, S Ultes, ...
arXiv preprint arXiv:1711.11023, 2017
Dialogue manager domain adaptation using gaussian process reinforcement learning
M Gašić, N Mrkšić, LM Rojas-Barahona, PH Su, S Ultes, D Vandyke, ...
Computer Speech & Language 45, 552-569, 2017
Sub-domain modelling for dialogue management with hierarchical reinforcement learning
P Budzianowski, S Ultes, PH Su, N Mrkšić, TH Wen, I Casanueva, ...
arXiv preprint arXiv:1706.06210, 2017
Feudal reinforcement learning for dialogue management in large domains
I Casanueva, P Budzianowski, PH Su, S Ultes, L Rojas-Barahona, ...
arXiv preprint arXiv:1803.03232, 2018
Emotions are a personal thing: Towards speaker-adaptive emotion recognition
M Sidorov, S Ultes, A Schmitt
2014 IEEE international conference on acoustics, speech and signal …, 2014
On quality ratings for spoken dialogue systems–experts vs. users
S Ultes, A Schmitt, W Minker
Proceedings of the 2013 Conference of the North American Chapter of the …, 2013
Towards quality-adaptive spoken dialogue management
S Ultes, A Schmitt, W Minker
NAACL-HLT Workshop on Future directions and needs in the Spoken Dialog …, 2012
Exploiting sentence and context representations in deep neural models for spoken language understanding
LMR Barahona, M Gasic, N Mrkšić, PH Su, S Ultes, TH Wen, S Young
arXiv preprint arXiv:1610.04120, 2016
Quality-adaptive spoken dialogue initiative selection and implications on reward modelling
S Ultes, M Kraus, A Schmitt, W Minker
Proceedings of the 16th Annual Meeting of the Special Interest Group on …, 2015
Domain-Independent User Satisfaction Reward Estimation for Dialogue Policy Learning.
S Ultes, P Budzianowski, I Casanueva, N Mrksic, LM Rojas-Barahona, ...
INTERSPEECH, 1721-1725, 2017
Managing adaptive spoken dialogue for intelligent environments
S Ultes, W Minker
Journal of Ambient Intelligence and Smart Environments 6 (5), 523-539, 2014
The system can't perform the operation now. Try again later.
Articles 1–20