16 citations · 60 across the 21 of their papers we have counts for
24 papers
Prompt reinforcing for long-term planning of large language models
Hsien-Chin Lin, Benjamin Matthias Ruppik, Carel van Niekerk +6
Large language models (LLMs) have achieved remarkable success in a wide range of natural language processing tasks and can be adapted through prompting. However, they remain subopt…
Post-Training Large Language Models via Reinforcement Learning from Self-Feedback
Carel van Niekerk, Renato Vukovic, Benjamin Ruppik +4
Large Language Models (LLMs) often produce plausible but poorly-calibrated answers, limiting their reliability on reasoning-intensive tasks. Recent research suggests that Chain-of-…
All Learning Has an Emotional Basis, So Does Task-Oriented Dialogue
Shutong Feng, Hsien-chin Lin, Nurul Lubis +5
Task-oriented dialogue (ToD) systems aim to help users accomplish goals through natural language interaction. Beyond task success, effective ToD systems must also maintain positive…
Local Topology Measures of Contextual Language Model Latent Spaces With Applications to Dialogue Term Extraction
Benjamin Matthias Ruppik, Michael Heck, Carel van Niekerk +5
A common approach for sequence tagging tasks based on contextual word representations is to train a machine learning classifier directly on these embedding vectors. This approach h…
Infusing Emotions into Task-oriented Dialogue Systems: Understanding, Management, and Generation
Shutong Feng, Hsien-chin Lin, Christian Geishauser +6
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 existing w…
Dialogue Ontology Relation Extraction via Constrained Chain-of-Thought Decoding
Renato Vukovic, David Arps, Carel van Niekerk +4
State-of-the-art task-oriented dialogue systems typically rely on task-specific ontologies for fulfilling user queries. The majority of task-oriented dialogue data, such as custome…
A Confidence-based Acquisition Model for Self-supervised Active Learning and Label Correction
Carel van Niekerk, Christian Geishauser, Michael Heck +6
Supervised neural approaches are hindered by their dependence on large, meticulously annotated datasets, a requirement that is particularly cumbersome for sequential tasks. The qua…
Affect Recognition in Conversations Using Large Language Models
Shutong Feng, Guangzhi Sun, Nurul Lubis +3
Affect recognition, encompassing emotions, moods, and feelings, plays a pivotal role in human communication. In the realm of conversational artificial intelligence, the ability to…
From Chatter to Matter: Addressing Critical Steps of Emotion Recognition Learning in Task-oriented Dialogue
Shutong Feng, Nurul Lubis, Benjamin Ruppik +6
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 dialogu…
EmoUS: Simulating User Emotions in Task-Oriented Dialogues
Hsien-Chin Lin, Shutong Feng, Christian Geishauser +6
Existing user simulators (USs) for task-oriented dialogue systems only model user behaviour on semantic and natural language levels without considering the user persona and emotion…
ChatGPT for Zero-shot Dialogue State Tracking: A Solution or an Opportunity?
Michael Heck, Nurul Lubis, Benjamin Ruppik +6
Recent research on dialogue state tracking (DST) focuses on methods that allow few- and zero-shot transfer to new domains or schemas. However, performance gains heavily depend on a…
Dialogue Evaluation with Offline Reinforcement Learning
Nurul Lubis, Christian Geishauser, Hsien-Chin Lin +4
Task-oriented dialogue systems aim to fulfill user goals through natural language interactions. They are ideally evaluated with human users, which however is unattainable to do at…
GenTUS: Simulating User Behaviour and Language in Task-oriented Dialogues with Generative Transformers
Hsien-Chin Lin, Christian Geishauser, Shutong Feng +4
User simulators (USs) are commonly used to train task-oriented dialogue systems (DSs) via reinforcement learning. The interactions often take place on semantic level for efficiency…
Dialogue Term Extraction using Transfer Learning and Topological Data Analysis
Renato Vukovic, Michael Heck, Benjamin Matthias Ruppik +3
Goal oriented dialogue systems were originally designed as a natural language interface to a fixed data-set of entities that users might inquire about, further described by domain,…
Dynamic Dialogue Policy for Continual Reinforcement Learning
Christian Geishauser, Carel van Niekerk, Nurul Lubis +4
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 an…
Robust Dialogue State Tracking with Weak Supervision and Sparse Data
Michael Heck, Nurul Lubis, Carel van Niekerk +4
Generalising dialogue state tracking (DST) to new data is especially challenging due to the strong reliance on abundant and fine-grained supervision during training. Sample sparsit…
What Does The User Want? Information Gain for Hierarchical Dialogue Policy Optimisation
Christian Geishauser, Songbo Hu, Hsien-chin Lin +5
The dialogue management component of a task-oriented dialogue system is typically optimised via reinforcement learning (RL). Optimisation via RL is highly susceptible to sample ine…
Uncertainty Measures in Neural Belief Tracking and the Effects on Dialogue Policy Performance
Carel van Niekerk, Andrey Malinin, Christian Geishauser +5
The ability to identify and resolve uncertainty is crucial for the robustness of a dialogue system. Indeed, this has been confirmed empirically on systems that utilise Bayesian app…
EmoWOZ: A Large-Scale Corpus and Labelling Scheme for Emotion Recognition in Task-Oriented Dialogue Systems
Shutong Feng, Nurul Lubis, Christian Geishauser +4
The ability to recognise emotions lends a conversational artificial intelligence a human touch. While emotions in chit-chat dialogues have received substantial attention, emotions…
Domain-independent User Simulation with Transformers for Task-oriented Dialogue Systems
Hsien-chin Lin, Nurul Lubis, Songbo Hu +5
Dialogue policy optimisation via reinforcement learning requires a large number of training interactions, which makes learning with real users time consuming and expensive. Many se…
Out-of-Task Training for Dialog State Tracking Models
Michael Heck, Carel van Niekerk, Nurul Lubis +4
Dialog state tracking (DST) suffers from severe data sparsity. While many natural language processing (NLP) tasks benefit from transfer learning and multi-task learning, in dialog…
LAVA: Latent Action Spaces via Variational Auto-encoding for Dialogue Policy Optimization
Nurul Lubis, Christian Geishauser, Michael Heck +4
Reinforcement learning (RL) can enable task-oriented dialogue systems to steer the conversation towards successful task completion. In an end-to-end setting, a response can be cons…
Knowing What You Know: Calibrating Dialogue Belief State Distributions via Ensembles
Carel van Niekerk, Michael Heck, Christian Geishauser +4
The ability to accurately track what happens during a conversation is essential for the performance of a dialogue system. Current state-of-the-art multi-domain dialogue state track…
TripPy: A Triple Copy Strategy for Value Independent Neural Dialog State Tracking
Michael Heck, Carel van Niekerk, Nurul Lubis +4
Task-oriented dialog systems rely on dialog state tracking (DST) to monitor the user's goal during the course of an interaction. Multi-domain and open-vocabulary settings complicat…