no code implementations • SIGDIAL (ACL) 2020 • Stefan Ultes, Wolfgang Maier
The differences in decision making between behavioural models of voice interfaces are hard to capture using existing measures for the absolute performance of such models.
no code implementations • SIGDIAL (ACL) 2021 • Stefan Ultes, Wolfgang Maier
Recently, principal reward components for dialogue policy reinforcement learning use task success and user satisfaction independently and neither the resulting learned behaviour has been analysed nor a suitable proper analysis method even existed.
1 code implementation • SIGDIAL (ACL) 2021 • Niklas Rach, Carolin Schindler, Isabel Feustel, Johannes Daxenberger, Wolfgang Minker, Stefan Ultes
Despite the remarkable progress in the field of computational argumentation, dialogue systems concerned with argumentative tasks often rely on structured knowledge about arguments and their relations.
no code implementations • LREC 2022 • Annalena Aicher, Wolfgang Minker, Stefan Ultes
To build a well-founded opinion it is natural for humans to gather and exchange new arguments.
no code implementations • LREC 2022 • Annalena Aicher, Nadine Gerstenlauer, Isabel Feustel, Wolfgang Minker, Stefan Ultes
We evaluate the likeability and motivation of users to interact with the new system in a user study.
no code implementations • LREC 2022 • Annalena Aicher, Nadine Gerstenlauer, Wolfgang Minker, Stefan Ultes
Most systems helping to provide structured information and support opinion building, discuss with users without considering their individual interest.
no code implementations • 3 Nov 2023 • Nicholas Thomas Walker, Stefan Ultes, Pierre Lison
After this conversion, the text representation of the dialogue state graph is included as part of the prompt of a large language model used to decode the agent response.
no code implementations • 20 Oct 2023 • Nicholas Thomas Walker, Stefan Ultes, Pierre Lison
Constructing responses in task-oriented dialogue systems typically relies on information sources such the current dialogue state or external databases.
no code implementations • 17 Aug 2023 • Klaus Weber, Annalena Aicher, Wolfang Minker, Stefan Ultes, Elisabeth André
To support a fair and unbiased opinion-building process, we propose a chatbot system that engages in a deliberative dialogue with a human.
no code implementations • 6 Aug 2023 • Ye Liu, Stefan Ultes, Wolfgang Minker, Wolfgang Maier
In this work, we study dialogue scenarios that start from chit-chat but eventually switch to task-related services, and investigate how a unified dialogue model, which can engage in both chit-chat and task-oriented dialogues, takes the initiative during the dialogue mode transition from chit-chat to task-oriented in a coherent and cooperative manner.
no code implementations • 4 Jul 2023 • Ye Liu, Stefan Ultes, Wolfgang Minker, Wolfgang Maier
We contribute two efficient prompt models which can proactively generate a transition sentence to trigger system-initiated transitions in a unified dialogue model.
1 code implementation • 23 Nov 2022 • Nicholas Thomas Walker, Stefan Ultes, Pierre Lison
We present a new approach to dialogue management using conversational knowledge graphs as core representation of the dialogue state.
no code implementations • 29 Sep 2022 • Ye Liu, Wolfgang Maier, Wolfgang Minker, Stefan Ultes
The pre-trained conversational models still fail to capture the implicit commonsense (CS) knowledge hidden in the dialogue interaction, even though they were pre-trained with an enormous dataset.
no code implementations • ICON 2021 • Ye Liu, Wolfgang Maier, Wolfgang Minker, Stefan Ultes
We utilize the pre-trained multi-context ConveRT model for context representation in a model trained from scratch; and leverage the immediate preceding user utterance for context generation in a model adapted from the pre-trained GPT-2.
no code implementations • 7 Sep 2021 • Ye Liu, Wolfgang Maier, Wolfgang Minker, Stefan Ultes
One challenge for dialogue agents is to recognize feelings of the conversation partner and respond accordingly.
no code implementations • RANLP 2021 • Ye Liu, Wolfgang Maier, Wolfgang Minker, Stefan Ultes
This paper presents an automatic method to evaluate the naturalness of natural language generation in dialogue systems.
no code implementations • 3 Mar 2021 • Waheed Ahmed Abro, Annalena Aicher, Niklas Rach, Stefan Ultes, Wolfgang Minker, Guilin Qi
Intent classifier model stacks BiLSTM with attention mechanism on top of the pre-trained BERT model and fine-tune the model for recognizing the user intent, whereas the argument similarity model employs BERT+BiLSTM for identifying system arguments the user refers to in his or her natural language utterances.
no code implementations • LREC 2020 • Juliana Miehle, Isabel Feustel, Julia Hornauer, Wolfgang Minker, Stefan Ultes
We use this corpus to estimate the elaborateness and the directness of each utterance.
no code implementations • LREC 2020 • Louisa Pragst, Wolfgang Minker, Stefan Ultes
Paraphrasing is an important aspect of natural-language generation that can produce more variety in the way specific content is presented.
no code implementations • LREC 2020 • Niklas Rach, Yuki Matsuda, Johannes Daxenberger, Stefan Ultes, Keiichi Yasumoto, Wolfgang Minker
We present an approach to evaluate argument search techniques in view of their use in argumentative dialogue systems by assessing quality aspects of the retrieved arguments.
no code implementations • WS 2019 • Stefan Ultes
Learning suitable and well-performing dialogue behaviour in statistical spoken dialogue systems has been in the focus of research for many years.
no code implementations • WS 2018 • Stefan Ultes, Paweł\ Budzianowski, Iñigo Casanueva, Lina Rojas-Barahona, Bo-Hsiang Tseng, Yen-chen Wu, Steve Young, Milica Gašić
Statistical spoken dialogue systems usually rely on a single- or multi-domain dialogue model that is restricted in its capabilities of modelling complex dialogue structures, e. g., relations.
1 code implementation • WS 2018 • Bo-Hsiang Tseng, Florian Kreyssig, Pawel Budzianowski, Inigo Casanueva, Yen-chen Wu, Stefan Ultes, Milica Gasic
Cross-domain natural language generation (NLG) is still a difficult task within spoken dialogue modelling.
1 code implementation • EMNLP 2018 • Pawe{\l} Budzianowski, Tsung-Hsien Wen, Bo-Hsiang Tseng, I{\~n}igo Casanueva, Stefan Ultes, Osman Ramadan, Milica Ga{\v{s}}i{\'c}
Even though machine learning has become the major scene in dialogue research community, the real breakthrough has been blocked by the scale of data available. To address this fundamental obstacle, we introduce the Multi-Domain Wizard-of-Oz dataset (MultiWOZ), a fully-labeled collection of human-human written conversations spanning over multiple domains and topics. At a size of 10k dialogues, it is at least one order of magnitude larger than all previous annotated task-oriented corpora. The contribution of this work apart from the open-sourced dataset is two-fold:firstly, a detailed description of the data collection procedure along with a summary of data structure and analysis is provided.
5 code implementations • EMNLP 2018 • Paweł Budzianowski, Tsung-Hsien Wen, Bo-Hsiang Tseng, Iñigo Casanueva, Stefan Ultes, Osman Ramadan, Milica Gašić
Even though machine learning has become the major scene in dialogue research community, the real breakthrough has been blocked by the scale of data available.
1 code implementation • WS 2018 • Lina Rojas-Barahona, Bo-Hsiang Tseng, Yinpei Dai, Clare Mansfield, Osman Ramadan, Stefan Ultes, Michael Crawford, Milica Gasic
In recent years, we have seen deep learning and distributed representations of words and sentences make impact on a number of natural language processing tasks, such as similarity, entailment and sentiment analysis.
no code implementations • WS 2018 • I{\~n}igo Casanueva, Pawe{\l} Budzianowski, Stefan Ultes, Florian Kreyssig, Bo-Hsiang Tseng, Yen-chen Wu, Milica Ga{\v{s}}i{\'c}
Reinforcement learning (RL) is a promising dialogue policy optimisation approach, but traditional RL algorithms fail to scale to large domains.
no code implementations • WS 2018 • Louisa Pragst, Stefan Ultes
In cooperative dialogues, identifying the intent of ones conversation partner and acting accordingly is of great importance.
no code implementations • 14 Jun 2018 • Lina M. Rojas-Barahona, Stefan Ultes, Pawel Budzianowski, Iñigo Casanueva, Milica Gasic, Bo-Hsiang Tseng, Steve Young
This paper presents two ways of dealing with scarce data in semantic decoding using N-Best speech recognition hypotheses.
no code implementations • NAACL 2018 • Iñigo Casanueva, Paweł Budzianowski, Pei-Hao Su, Stefan Ultes, Lina Rojas-Barahona, Bo-Hsiang Tseng, Milica Gašić
Reinforcement learning (RL) is a promising approach to solve dialogue policy optimisation.
no code implementations • 29 Nov 2017 • Iñigo Casanueva, Paweł Budzianowski, Pei-Hao Su, Nikola Mrkšić, Tsung-Hsien Wen, Stefan Ultes, Lina Rojas-Barahona, Steve Young, Milica Gašić
Dialogue assistants are rapidly becoming an indispensable daily aid.
no code implementations • IJCNLP 2017 • Louisa Pragst, Koichiro Yoshino, Wolfgang Minker, Satoshi Nakamura, Stefan Ultes
Defining all possible system actions in a dialogue system by hand is a tedious work.
Cultural Vocal Bursts Intensity Prediction Spoken Dialogue Systems
no code implementations • WS 2017 • Kyusong Lee, Tiancheng Zhao, Yulun Du, Edward Cai, Allen Lu, Eli Pincus, David Traum, Stefan Ultes, Lina M. Rojas-Barahona, Milica Gasic, Steve Young, Maxine Eskenazi
DialPort collects user data for connected spoken dialog systems.
no code implementations • WS 2017 • Niklas Rach, Wolfgang Minker, Stefan Ultes
For estimating the Interaction Quality (IQ) in Spoken Dialogue Systems (SDS), the dialogue history is of significant importance.
no code implementations • WS 2017 • Stefan Ultes, Paweł Budzianowski, Iñigo Casanueva, Nikola Mrkšić, Lina Rojas-Barahona, Pei-Hao Su, Tsung-Hsien Wen, Milica Gašić, Steve Young
Reinforcement learning is widely used for dialogue policy optimization where the reward function often consists of more than one component, e. g., the dialogue success and the dialogue length.
Multi-Objective Reinforcement Learning reinforcement-learning +1
no code implementations • WS 2017 • Pei-Hao Su, Pawel Budzianowski, Stefan Ultes, Milica Gasic, Steve Young
Firstly, to speed up the learning process, two sample-efficient neural networks algorithms: trust region actor-critic with experience replay (TRACER) and episodic natural actor-critic with experience replay (eNACER) are presented.
no code implementations • WS 2017 • Paweł Budzianowski, Stefan Ultes, Pei-Hao Su, Nikola Mrkšić, Tsung-Hsien Wen, Iñigo Casanueva, Lina Rojas-Barahona, Milica Gašić
In doing that, we show that our approach has the potential to facilitate policy optimisation for more sophisticated multi-domain dialogue systems.
no code implementations • COLING 2016 • Lina M. Rojas Barahona, Milica Gasic, Nikola Mrkšić, Pei-Hao Su, Stefan Ultes, Tsung-Hsien Wen, Steve Young
This paper presents a deep learning architecture for the semantic decoder component of a Statistical Spoken Dialogue System.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +6
no code implementations • 9 Sep 2016 • Milica Gasic, Nikola Mrksic, Lina M. Rojas-Barahona, Pei-Hao Su, Stefan Ultes, David Vandyke, Tsung-Hsien Wen, Steve Young
Spoken dialogue systems allow humans to interact with machines using natural speech.
no code implementations • EMNLP 2016 • Tsung-Hsien Wen, Milica Gasic, Nikola Mrksic, Lina M. Rojas-Barahona, Pei-Hao Su, Stefan Ultes, David Vandyke, Steve Young
Recently a variety of LSTM-based conditional language models (LM) have been applied across a range of language generation tasks.
no code implementations • 8 Jun 2016 • Pei-Hao Su, Milica Gasic, Nikola Mrksic, Lina Rojas-Barahona, Stefan Ultes, David Vandyke, Tsung-Hsien Wen, Steve Young
We describe a two-step approach for dialogue management in task-oriented spoken dialogue systems.
no code implementations • ACL 2016 • Pei-Hao Su, Milica Gasic, Nikola Mrksic, Lina Rojas-Barahona, Stefan Ultes, David Vandyke, Tsung-Hsien Wen, Steve Young
The ability to compute an accurate reward function is essential for optimising a dialogue policy via reinforcement learning.
1 code implementation • EACL 2017 • Tsung-Hsien Wen, David Vandyke, Nikola Mrksic, Milica Gasic, Lina M. Rojas-Barahona, Pei-Hao Su, Stefan Ultes, Steve Young
Teaching machines to accomplish tasks by conversing naturally with humans is challenging.
no code implementations • LREC 2014 • Stefan Ultes, H{\"u}seyin Dikme, Wolfgang Minker
While Spoken Dialogue Systems have gained in importance in recent years, most systems applied in the real world are still static and error-prone.
no code implementations • LREC 2014 • Maxim Sidorov, Stefan Ultes, Alex Schmitt, er
In this contribution, we argue that adding information unique for each speaker, i. e., by using speaker identification techniques, improves emotion recognition simply by adding this additional information to the feature vector of the statistical classification algorithm.
no code implementations • LREC 2012 • Alex Schmitt, er, Stefan Ultes, Wolfgang Minker
Standardized corpora are the foundation for spoken language research.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +3