" Do you follow me?": A Survey of Recent Approaches in Dialogue State Tracking

L Jacqmin, LM Rojas-Barahona, B Favre - arxiv preprint arxiv:2207.14627, 2022 - arxiv.org
While communicating with a user, a task-oriented dialogue system has to track the user's
needs at each turn according to the conversation history. This process called dialogue state …

Dynamic dialogue policy for continual reinforcement learning

C Geishauser, C van Niekerk, N Lubis, M Heck… - arxiv preprint arxiv …, 2022 - arxiv.org
Continual learning is one of the key components of human learning and a necessary
requirement of artificial intelligence. As dialogue can potentially span infinitely many topics …

Infusing emotions into task-oriented dialogue systems: Understanding, management, and generation

S Feng, H Lin, C Geishauser, N Lubis… - arxiv preprint arxiv …, 2024 - arxiv.org
Emotions are indispensable in human communication, but are often overlooked in task-
oriented dialogue (ToD) modelling, where the task success is the primary focus. While …

Confidence estimation for llm-based dialogue state tracking

YJ Sun, S Dey, D Hakkani-Tür… - 2024 IEEE Spoken …, 2024 - ieeexplore.ieee.org
Estimation of a model's confidence on its outputs is critical for Conversational AI systems
based on large language models (LLMs), especially for reducing hallucination and …

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

S Feng, N Lubis, B Ruppik, C Geishauser… - arxiv preprint arxiv …, 2023 - arxiv.org
Emotion recognition in conversations (ERC) is a crucial task for building human-like
conversational agents. While substantial efforts have been devoted to ERC for chit-chat …

[PDF][PDF] User simulation in task-oriented dialog systems based on large language models via in-context learning

R Horst - 2024 - fbmn.h-da.de
The growing importance of human-computer interaction and natural language processing is
highlighted by significant advances such as the introduction of ChatGPT, a Large Language …

CAMELL: Confidence-based Acquisition Model for Efficient Self-supervised Active Learning with Label Validation

C van Niekerk, C Geishauser, M Heck, S Feng… - arxiv preprint arxiv …, 2023 - arxiv.org
Supervised neural approaches are hindered by their dependence on large, meticulously
annotated datasets, a requirement that is particularly cumbersome for sequential tasks. The …

Ontology Construction for Task-oriented Dialogue

R Vukovic - Proceedings of the 20th Workshop of Young …, 2024 - aclanthology.org
Ontology Construction for Task-oriented Dialogue Page 1 The 20th Annual Meeting of the
Young Researchers’ Roundtable on Spoken Dialogue Systems, pages 53–56 September …

Span-prediction of Unknown Values for Long-sequence Dialogue State Tracking

MN Dorabati, R Ramezani… - 2022 12th International …, 2022 - ieeexplore.ieee.org
Dialogue state tracking is one of the main components in task-oriented dialogue systems
whose duty is to track the user's goal during the conversation. Due to the diversity in natural …

Towards Emotion-aware Task-oriented Dialogue Systems in the Era of Large Language Models

S Feng - Proceedings of the 20th Workshop of Young …, 2024 - aclanthology.org
My research interests lie in the area of modelling affective behaviours of interlocutors in
conversations. In particular, I look at emotion perception, expression, and management in …