Dynamic dialogue modelling

Informations projet

DYMO

N° de convention de subvention: 804636

DOI

10.3030/804636

Date de signature de la CE 24 Octobre 2018

Date de début 1 Septembre 2019

Date de fin 31 Janvier 2026

Financé au titre de

• EXCELLENT SCIENCE - European Research Council (ERC)

Coût total

€ 1 499 956,00

Contribution de l’UE

€ 1 499 956,00

Coordonné par

HEINRICH-HEINE-UNIVERSITAET DUESSELDORF
Germany

CORDIS fournit des liens vers les livrables publics et les publications des projets HORIZON.

Les liens vers les livrables et les publications des projets du 7e PC, ainsi que les liens vers certains types de résultats spécifiques tels que les jeux de données et les logiciels, sont récupérés dynamiquement sur OpenAIRE .

Publications

Peer reviewed articles (3)

A Confidence-based Acquisition Model for Self-supervised Active Learning and Label Correction

Auteurs: Carel van Niekerk, Christian Geishauser, Michael Heck, Shutong Feng, Hsien-chin Lin, Nurul Lubis, Benjamin Ruppik, Renato Vukovic, Milica Gašić
Publié dans: Transactions of the Association for Computational Linguistics, Numéro 13, 2025, Page(s) 167-187, ISSN 2307-387X
Éditeur: MIT Press
DOI: 10.1162/tacl_a_00734

Learning with an Open Horizon in Ever-Changing Dialogue Circumstances

Auteurs: Christian Geishauser; Carel van Niekerk; Nurul Lubis; Hsien-chin Lin; Michael Heck; Shutong Feng; Benjamin Ruppik; Renato Vukovic; Milica Gasic
Publié dans: IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2024, ISSN 2329-9290
Éditeur: IEEE Advancing Technology for Humanity
DOI: 10.1109/taslp.2024.3385289

Learning from Noisy Labels via Self-Taught On-the-Fly Meta Loss Rescaling

Auteurs: Michael Heck, Christian Geishauser, Nurul Lubis, Carel Van Niekerk, Shutong Feng, Hsien-Chin Lin, Benjamin Matthias Ruppik, Renato Vukovic, Milica Gasic
Publié dans: Proceedings of the AAAI Conference on Artificial Intelligence, Numéro 39, 2025, Page(s) 24059-24068, ISSN 2374-3468
Éditeur: Association for the Advancement of Artificial Intelligence (AAAI)
DOI: 10.1609/aaai.v39i22.34580

Conference proceedings (25)

Local Topology Measures of Contextual Language Model Latent Spaces with Applications to Dialogue Term Extraction

Auteurs: Benjamin Matthias Ruppik, Michael Heck, Carel van Niekerk, Renato Vukovic, Hsien-chin Lin, Shutong Feng, Marcus Zibrowius, Milica Gasic
Publié dans: Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue, 2025, Page(s) 344-356
Éditeur: Association for Computational Linguistics, SIGDIAL 2024
DOI: 10.18653/v1/2024.sigdial-1.31

Uncertainty Measures in Neural Belief Tracking and the Effects on Dialogue Policy Performance

Auteurs: Carel van Niekerk, Andrey Malinin, Christian Geishauser, Michael Heck, Hsien-chin Lin, Nurul Lubis, Shutong Feng and Milica Gašic
Publié dans: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2021, Page(s) 7901–7914
Éditeur: Association for Computational Linguistics
DOI: 10.18653/v1/2021.emnlp-main.623

LAVA: Latent Action Spaces via Variational Auto-encoding for Dialogue Policy Optimization

Auteurs: N. Lubis, C. Geishauser, M. Heck, H-C. Lin, M. Moresi, C. van Niekerk, M. Gašić
Publié dans: Proceedings of the 28th International Conference on Computational Linguistics (COLING), 2020, Page(s) 465–479
Éditeur: International Committee on Computational Linguistics
DOI: 10.18653/v1/2020.coling-main.41

Dialogue Term Extraction using Transfer Learning and Topological Data Analysis

Auteurs: Renato Vukovic, Michael Heck, Benjamin Ruppik, Carel van Niekerk, Marcus Zibrowius, Milica Gasic
Publié dans: 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue, 2022
Éditeur: Association for Computational Linguistics (ACL)
DOI: 10.5281/zenodo.6858565

Dialogue Evaluation with Offline Reinforcement Learning

Auteurs: Nurul Lubis, Christian Geishauser, Hsien-Chin Lin, Carel van Niekerk, Michael Heck, Shutong Feng, Milica Gasic
Publié dans: 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue, 2022
Éditeur: Association for Computational Linguistics (ACL)
DOI: 10.48550/arxiv.2209.00876

ConvLab-3: A Flexible Dialogue System Toolkit Based on a Unified Data Format

Auteurs: Qi Zhu, Christian Geishauser, Hsien-chin Lin, Carel van Niekerk, Baolin Peng, Zheng Zhang, Shutong Feng, Michael Heck, Nurul Lubis, Dazhen Wan, Xiaochen Zhu, Jianfeng Gao, Milica Gasic, Minlie Huang
Publié dans: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, 2023
Éditeur: Association for Computational Linguistics
DOI: 10.18653/v1/2023.emnlp-demo.9

Robust Dialogue State Tracking with Weak Supervision and Sparse Data

Auteurs: Michael Heck, Nurul Lubis, Carel van Niekerk, Shutong Feng, Christian Geishauser, Hsien-Chin Lin, Milica Gasic
Publié dans: Transactions of the Association for Computational Linguistics, 2022
Éditeur: MIT Press
DOI: 10.1162/tacl_a_00513

Actor-Double-Critic: Incorporating Model-Based Critic for Task-Oriented Dialogue Systems

Auteurs: Y.-C. Wu, B.-H. Tseng, M. Gašić
Publié dans: Findings of EMNLP 2020, 2020, Page(s) 854–863
Éditeur: Association for Computational Linguistics
DOI: 10.18653/v1/2020.findings-emnlp.75

Less is More: Local Intrinsic Dimensions of Contextual Language Models

Auteurs: Benjamin Matthias Ruppik, Julius von Rohrscheidt, Carel van Niekerk, Michael Heck, Renato Vukovic, Shutong Feng, Hsien-chin Lin, Nurul Lubis, Bastian Rieck, Marcus Zibrowius, Milica Gašić
Publié dans: 2025
Éditeur: NeurIPS 2025
DOI: 10.48550/arxiv.2506.01034

EmoWOZ: A Large-Scale Corpus and Labelling Scheme for Emotion Recognition in Task-Oriented Dialogue Systems

Auteurs: Feng, Shutong; Lubis, Nurul; Geishauser, Christian; Lin, Hsien-chin; Heck, Michael; van Niekerk, Carel; Gašić, Milica
Publié dans: Proceedings of the 13th Conference on Language Resources and Evaluation (LREC 2022), Numéro 1, 2022, Page(s) 4096–4113
Éditeur: European Language Resources Association (ELRA)
DOI: 10.48550/arxiv.2109.04919

Speech-based Slot Filling using Large Language Models

Auteurs: Guangzhi Sun, Shutong Feng, Dongcheng Jiang, Chao Zhang, Milica Gasic, Phil Woodland
Publié dans: Findings of the Association for Computational Linguistics ACL 2024, 2024, Page(s) 6351-6362
Éditeur: Association for Computational Linguistics
DOI: 10.18653/v1/2024.findings-acl.379

Infusing Emotions into Task-oriented Dialogue Systems: Understanding, Management, and Generation

Auteurs: Shutong Feng, Hsien-chin Lin, Christian Geishauser, Nurul Lubis, Carel van Niekerk, Michael Heck, Benjamin Ruppik, Renato Vukovic, Milica Gašić
Publié dans: Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue, 2025, Page(s) 699-717
Éditeur: Association for Computational Linguistics, SIGDIAL 2024
DOI: 10.18653/v1/2024.sigdial-1.60

Knowing What You Know: Calibrating Dialogue Belief State Distributions via Ensembles

Auteurs: Carel van Niekerk, Michael Heck, Christian Geishauser, Hsien-chin Lin, Nurul Lubis, Marco Moresi, Milica Gasic
Publié dans: Findings of the Association for Computational Linguistics: EMNLP 2020, 2020, Page(s) 3096-3102
Éditeur: Association for Computational Linguistics
DOI: 10.18653/v1/2020.findings-emnlp.277

ChatGPT for Zero-shot Dialogue State Tracking: A Solution or an Opportunity?

Auteurs: Michael Heck, Nurul Lubis, Benjamin Ruppik, Renato Vukovic, Shutong Feng, Christian Geishauser, Hsien-chin Lin, Carel van Niekerk, Milica Gasic
Publié dans: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), 2023
Éditeur: Association for Computational Linguistics
DOI: 10.18653/v1/2023.acl-short.81

Out-of-Task Training for Dialog State Tracking Models

Auteurs: M. Heck, C. Geishauser, H-C. Lin, N. Lubis, M. Moresi, C. van Niekerk, M. Gašić
Publié dans: COLING 2020, 2020, Page(s) 6767–6774
Éditeur: International Committee on Computational Linguistics
DOI: 10.18653/v1/2020.coling-main.596

What does the User Want? Information Gain for Hierarchical Dialogue Policy Optimisation

Auteurs: C. Geishauser, S. Hu, H. Lin, N. Lubis, M. Heck, S. Feng, C. van Niekerk, M. Gasic
Publié dans: IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), 2021
Éditeur: IEEE
DOI: 10.1109/asru51503.2021.9687856

Affect Recognition in Conversations Using Large Language Models

Auteurs: Shutong Feng, Guangzhi Sun, Nurul Lubis, Wen Wu, Chao Zhang, Milica Gasic
Publié dans: Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue, 2025, Page(s) 259-273
Éditeur: Association for Computational Linguistics, SIGDIAL 2024
DOI: 10.18653/v1/2024.sigdial-1.23

From Chatter to Matter: Addressing Critical Steps of Emotion Recognition Learning in Task-oriented Dialogue

Auteurs: Shutong Feng, Nurul Lubis, Benjamin Ruppik, Christian Geishauser, Michael Heck, Hsien-chin Lin, Carel van Niekerk, Renato Vukovic, Milica Gasic
Publié dans: Proceedings of the 24th Annual Meeting of the Special Interest Group on Discourse and Dialogue, 2023
Éditeur: Association for Computational Linguistics
DOI: 10.18653/v1/2023.sigdial-1.8

GenTUS: Simulating User Behaviour and Language in Task-oriented Dialogues with Generative Transformers

Auteurs: Hsien-Chin Lin, Christian Geishauser, Shutong Feng, Nurul Lubis, Carel van Niekerk, Michael Heck and Milica Gasic
Publié dans: 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue, 2022
Éditeur: The Association for Computational Linguistics (ACL)
DOI: 10.48550/arxiv.2208.10817

EmoUS: Simulating User Emotions in Task-Oriented Dialogues

Auteurs: Hsien-Chin Lin, Shutong Feng, Christian Geishauser, Nurul Lubis, Carel van Niekerk, Michael Heck, Benjamin Ruppik, Renato Vukovic, Milica Gasić
Publié dans: SIGIR '23: Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2023
Éditeur: Association for Computing Machinery
DOI: 10.1145/3539618.3592092

Dynamic Dialogue Policy for Continual Reinforcement Learning

Auteurs: Christian Geishauser, Carel van Niekerk, Nurul Lubis, Michael Heck, Hsien-Chin Lin, Shutong Feng, Milica Gasic
Publié dans: The 29th International Conference on Computational Linguistics (COLING), 2022
Éditeur: International Committee on Computational Linguistics
DOI: 10.48550/arxiv.2204.05928

Dialogue Ontology Relation Extraction via Constrained Chain-of-Thought Decoding

Auteurs: Renato Vukovic, David Arps, Carel van Niekerk, Benjamin Matthias Ruppik, Hsien-Chin Lin, Michael Heck, Milica Gašić
Publié dans: Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue, 2024
Éditeur: Association for Computational Linguistics, SIGDIAL 2024
DOI: 10.48550/arxiv.2408.02361

Topology of Word Embeddings: Singularities Reflect Polysemy

Auteurs: A. Jakubowski, M. Gašić, M. Zibrowius
Publié dans: *SEM 2020, 2020
Éditeur: Association for Computational Linguistics
DOI: 10.48550/arxiv.2011.09413

TripPy: A Triple Copy Strategy for Value Independent Neural Dialog State Tracking

Auteurs: M. Heck, C. van Niekerk, N. Lubis, C. Geishauser, H-C. Lin, M. Moresi, M. Gašić
Publié dans: Proceedings of the 21th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL)), 2020, Page(s) 35–44
Éditeur: Association for Computational Linguistics
DOI: 10.18653/v1/2020.sigdial-1.4

Domain-independent User Simulation with Transformers for Task-oriented Dialogue Systems

Auteurs: Lin, Hsien-chin; Lubis, Nurul; Hu, Songbo; van Niekerk, Carel; Geishauser, Christian; Heck, Michael; Feng, Shutong; Gašić, Milica
Publié dans: Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL), 2021, Page(s) 445–456
Éditeur: Association for Computational Linguistics
DOI: 10.18653/v1/2021.sigdial-1.47