Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Stefan Ultes

Stefan Ultes

Natural Language Understanding for Argumentative Dialogue Systems in the Opinion Building Domain


Mar 03, 2021
Waheed Ahmed Abro, Annalena Aicher, Niklas Rach, Stefan Ultes, Wolfgang Minker, Guilin Qi

Figure 1 for Natural Language Understanding for Argumentative Dialogue Systems in the Opinion Building Domain
Figure 2 for Natural Language Understanding for Argumentative Dialogue Systems in the Opinion Building Domain
Figure 3 for Natural Language Understanding for Argumentative Dialogue Systems in the Opinion Building Domain
Figure 4 for Natural Language Understanding for Argumentative Dialogue Systems in the Opinion Building Domain

  Access Paper or Ask Questions

Improving Interaction Quality Estimation with BiLSTMs and the Impact on Dialogue Policy Learning


Jan 21, 2020
Stefan Ultes

Figure 1 for Improving Interaction Quality Estimation with BiLSTMs and the Impact on Dialogue Policy Learning
Figure 2 for Improving Interaction Quality Estimation with BiLSTMs and the Impact on Dialogue Policy Learning
Figure 3 for Improving Interaction Quality Estimation with BiLSTMs and the Impact on Dialogue Policy Learning
Figure 4 for Improving Interaction Quality Estimation with BiLSTMs and the Impact on Dialogue Policy Learning
* Published at SIGDIAL 2019 
  Access Paper or Ask Questions

Addressing Objects and Their Relations: The Conversational Entity Dialogue Model


Jan 05, 2019
Stefan Ultes, Paweł\ Budzianowski, Iñigo Casanueva, Lina Rojas-Barahona, Bo-Hsiang Tseng, Yen-Chen Wu, Steve Young, Milica Gašić

Figure 1 for Addressing Objects and Their Relations: The Conversational Entity Dialogue Model
Figure 2 for Addressing Objects and Their Relations: The Conversational Entity Dialogue Model
Figure 3 for Addressing Objects and Their Relations: The Conversational Entity Dialogue Model
Figure 4 for Addressing Objects and Their Relations: The Conversational Entity Dialogue Model
* Accepted at SIGDial 2018 
  Access Paper or Ask Questions

Variational Cross-domain Natural Language Generation for Spoken Dialogue Systems


Dec 20, 2018
Bo-Hsiang Tseng, Florian Kreyssig, Pawel Budzianowski, Inigo Casanueva, Yen-Chen Wu, Stefan Ultes, Milica Gasic

Figure 1 for Variational Cross-domain Natural Language Generation for Spoken Dialogue Systems
Figure 2 for Variational Cross-domain Natural Language Generation for Spoken Dialogue Systems
Figure 3 for Variational Cross-domain Natural Language Generation for Spoken Dialogue Systems
Figure 4 for Variational Cross-domain Natural Language Generation for Spoken Dialogue Systems
* Sigdial 2018 
  Access Paper or Ask Questions

MultiWOZ - A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling


Sep 29, 2018
Paweł Budzianowski, Tsung-Hsien Wen, Bo-Hsiang Tseng, Iñigo Casanueva, Stefan Ultes, Osman Ramadan, Milica Gašić

Figure 1 for MultiWOZ - A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling
Figure 2 for MultiWOZ - A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling
Figure 3 for MultiWOZ - A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling
Figure 4 for MultiWOZ - A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling
* Accepted for publication at EMNLP 2018 
  Access Paper or Ask Questions

Deep learning for language understanding of mental health concepts derived from Cognitive Behavioural Therapy


Sep 03, 2018
Lina Rojas-Barahona, Bo-Hsiang Tseng, Yinpei Dai, Clare Mansfield, Osman Ramadan, Stefan Ultes, Michael Crawford, Milica Gasic

Figure 1 for Deep learning for language understanding of mental health concepts derived from Cognitive Behavioural Therapy
Figure 2 for Deep learning for language understanding of mental health concepts derived from Cognitive Behavioural Therapy
Figure 3 for Deep learning for language understanding of mental health concepts derived from Cognitive Behavioural Therapy
Figure 4 for Deep learning for language understanding of mental health concepts derived from Cognitive Behavioural Therapy
* Accepted for publication at LOUHI 2018: The Ninth International Workshop on Health Text Mining and Information Analysis 
  Access Paper or Ask Questions

Nearly Zero-Shot Learning for Semantic Decoding in Spoken Dialogue Systems


Jun 21, 2018
Lina M. Rojas-Barahona, Stefan Ultes, Pawel Budzianowski, Iñigo Casanueva, Milica Gasic, Bo-Hsiang Tseng, Steve Young

Figure 1 for Nearly Zero-Shot Learning for Semantic Decoding in Spoken Dialogue Systems
Figure 2 for Nearly Zero-Shot Learning for Semantic Decoding in Spoken Dialogue Systems
Figure 3 for Nearly Zero-Shot Learning for Semantic Decoding in Spoken Dialogue Systems
Figure 4 for Nearly Zero-Shot Learning for Semantic Decoding in Spoken Dialogue Systems

  Access Paper or Ask Questions

A Benchmarking Environment for Reinforcement Learning Based Task Oriented Dialogue Management


Apr 06, 2018
Iñigo Casanueva, Paweł Budzianowski, Pei-Hao Su, Nikola Mrkšić, Tsung-Hsien Wen, Stefan Ultes, Lina Rojas-Barahona, Steve Young, Milica Gašić

Figure 1 for A Benchmarking Environment for Reinforcement Learning Based Task Oriented Dialogue Management
Figure 2 for A Benchmarking Environment for Reinforcement Learning Based Task Oriented Dialogue Management
Figure 3 for A Benchmarking Environment for Reinforcement Learning Based Task Oriented Dialogue Management
Figure 4 for A Benchmarking Environment for Reinforcement Learning Based Task Oriented Dialogue Management
* Accepted at the Deep Reinforcement Learning Symposium, 31st Conference on Neural Information Processing Systems (NIPS 2017) Paper updated with minor changes 
  Access Paper or Ask Questions

Feudal Reinforcement Learning for Dialogue Management in Large Domains


Mar 08, 2018
Iñigo Casanueva, Paweł Budzianowski, Pei-Hao Su, Stefan Ultes, Lina Rojas-Barahona, Bo-Hsiang Tseng, Milica Gašić

Figure 1 for Feudal Reinforcement Learning for Dialogue Management in Large Domains
Figure 2 for Feudal Reinforcement Learning for Dialogue Management in Large Domains
Figure 3 for Feudal Reinforcement Learning for Dialogue Management in Large Domains
Figure 4 for Feudal Reinforcement Learning for Dialogue Management in Large Domains
* Accepted as a short paper in NAACL 2018 
  Access Paper or Ask Questions

Reward-Balancing for Statistical Spoken Dialogue Systems using Multi-objective Reinforcement Learning


Jul 19, 2017
Stefan Ultes, Paweł Budzianowski, Iñigo Casanueva, Nikola Mrkšić, Lina Rojas-Barahona, Pei-Hao Su, Tsung-Hsien Wen, Milica Gašić, Steve Young

Figure 1 for Reward-Balancing for Statistical Spoken Dialogue Systems using Multi-objective Reinforcement Learning
Figure 2 for Reward-Balancing for Statistical Spoken Dialogue Systems using Multi-objective Reinforcement Learning
Figure 3 for Reward-Balancing for Statistical Spoken Dialogue Systems using Multi-objective Reinforcement Learning
* Accepted at SIGDial 2017 
  Access Paper or Ask Questions

Sub-domain Modelling for Dialogue Management with Hierarchical Reinforcement Learning


Jul 17, 2017
Paweł Budzianowski, Stefan Ultes, Pei-Hao Su, Nikola Mrkšić, Tsung-Hsien Wen, Iñigo Casanueva, Lina Rojas-Barahona, Milica Gašić

Figure 1 for Sub-domain Modelling for Dialogue Management with Hierarchical Reinforcement Learning
Figure 2 for Sub-domain Modelling for Dialogue Management with Hierarchical Reinforcement Learning
Figure 3 for Sub-domain Modelling for Dialogue Management with Hierarchical Reinforcement Learning
Figure 4 for Sub-domain Modelling for Dialogue Management with Hierarchical Reinforcement Learning
* Update of the section 4 and the bibliography 
  Access Paper or Ask Questions

Sample-efficient Actor-Critic Reinforcement Learning with Supervised Data for Dialogue Management


Jul 05, 2017
Pei-Hao Su, Pawel Budzianowski, Stefan Ultes, Milica Gasic, Steve Young

Figure 1 for Sample-efficient Actor-Critic Reinforcement Learning with Supervised Data for Dialogue Management
Figure 2 for Sample-efficient Actor-Critic Reinforcement Learning with Supervised Data for Dialogue Management
Figure 3 for Sample-efficient Actor-Critic Reinforcement Learning with Supervised Data for Dialogue Management
Figure 4 for Sample-efficient Actor-Critic Reinforcement Learning with Supervised Data for Dialogue Management
* Accepted as a long paper in SigDial 2017 
  Access Paper or Ask Questions

A Network-based End-to-End Trainable Task-oriented Dialogue System


Apr 24, 2017
Tsung-Hsien Wen, David Vandyke, Nikola Mrksic, Milica Gasic, Lina M. Rojas-Barahona, Pei-Hao Su, Stefan Ultes, Steve Young

* published at EACL 2017 
  Access Paper or Ask Questions

Exploiting Sentence and Context Representations in Deep Neural Models for Spoken Language Understanding


Oct 13, 2016
Lina M. Rojas Barahona, Milica Gasic, Nikola Mrkšić, Pei-Hao Su, Stefan Ultes, Tsung-Hsien Wen, Steve Young

Figure 1 for Exploiting Sentence and Context Representations in Deep Neural Models for Spoken Language Understanding
Figure 2 for Exploiting Sentence and Context Representations in Deep Neural Models for Spoken Language Understanding
Figure 3 for Exploiting Sentence and Context Representations in Deep Neural Models for Spoken Language Understanding
Figure 4 for Exploiting Sentence and Context Representations in Deep Neural Models for Spoken Language Understanding

  Access Paper or Ask Questions

Dialogue manager domain adaptation using Gaussian process reinforcement learning


Sep 09, 2016
Milica Gasic, Nikola Mrksic, Lina M. Rojas-Barahona, Pei-Hao Su, Stefan Ultes, David Vandyke, Tsung-Hsien Wen, Steve Young

Figure 1 for Dialogue manager domain adaptation using Gaussian process reinforcement learning
Figure 2 for Dialogue manager domain adaptation using Gaussian process reinforcement learning
Figure 3 for Dialogue manager domain adaptation using Gaussian process reinforcement learning
Figure 4 for Dialogue manager domain adaptation using Gaussian process reinforcement learning
* accepted for publication in Computer Speech and Language 
  Access Paper or Ask Questions

Conditional Generation and Snapshot Learning in Neural Dialogue Systems


Jun 10, 2016
Tsung-Hsien Wen, Milica Gasic, Nikola Mrksic, Lina M. Rojas-Barahona, Pei-Hao Su, Stefan Ultes, David Vandyke, Steve Young

Figure 1 for Conditional Generation and Snapshot Learning in Neural Dialogue Systems
Figure 2 for Conditional Generation and Snapshot Learning in Neural Dialogue Systems
Figure 3 for Conditional Generation and Snapshot Learning in Neural Dialogue Systems
Figure 4 for Conditional Generation and Snapshot Learning in Neural Dialogue Systems

  Access Paper or Ask Questions

Continuously Learning Neural Dialogue Management


Jun 08, 2016
Pei-Hao Su, Milica Gasic, Nikola Mrksic, Lina Rojas-Barahona, Stefan Ultes, David Vandyke, Tsung-Hsien Wen, Steve Young

Figure 1 for Continuously Learning Neural Dialogue Management
Figure 2 for Continuously Learning Neural Dialogue Management
Figure 3 for Continuously Learning Neural Dialogue Management
Figure 4 for Continuously Learning Neural Dialogue Management

  Access Paper or Ask Questions

On-line Active Reward Learning for Policy Optimisation in Spoken Dialogue Systems


Jun 02, 2016
Pei-Hao Su, Milica Gasic, Nikola Mrksic, Lina Rojas-Barahona, Stefan Ultes, David Vandyke, Tsung-Hsien Wen, Steve Young

Figure 1 for On-line Active Reward Learning for Policy Optimisation in Spoken Dialogue Systems
Figure 2 for On-line Active Reward Learning for Policy Optimisation in Spoken Dialogue Systems
Figure 3 for On-line Active Reward Learning for Policy Optimisation in Spoken Dialogue Systems
Figure 4 for On-line Active Reward Learning for Policy Optimisation in Spoken Dialogue Systems
* Accepted as a long paper in ACL 2016 
  Access Paper or Ask Questions