Michael Heck
YOU?
Author Swipe
View article: Prompt reinforcing for long-term planning of large language models
Prompt reinforcing for long-term planning of large language models Open
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 suboptimal in multi-turn interactions, often relying on incorrect…
View article: Text-to-SQL Task-oriented Dialogue Ontology Construction
Text-to-SQL Task-oriented Dialogue Ontology Construction Open
Large language models (LLMs) are widely used as general-purpose knowledge sources, but they rely on parametric knowledge, limiting explainability and trustworthiness. In task-oriented dialogue (TOD) systems, this separation is explicit, us…
View article: Less is More: Local Intrinsic Dimensions of Contextual Language Models
Less is More: Local Intrinsic Dimensions of Contextual Language Models Open
Understanding the internal mechanisms of large language models (LLMs) remains a challenging and complex endeavor. Even fundamental questions, such as how fine-tuning affects model behavior, often require extensive empirical evaluation. In …
View article: Learning from Noisy Labels via Self-Taught On-the-Fly Meta Loss Rescaling
Learning from Noisy Labels via Self-Taught On-the-Fly Meta Loss Rescaling Open
Correct labels are indispensable for training effective machine learning models. However, creating high-quality labels is expensive, and even professionally labeled data contains errors and ambiguities. Filtering and denoising can be appli…
View article: A Confidence-based Acquisition Model for Self-supervised Active Learning and Label Correction
A Confidence-based Acquisition Model for Self-supervised Active Learning and Label Correction Open
Supervised neural approaches are hindered by their dependence on large, meticulously annotated datasets, a requirement that is particularly cumbersome for sequential tasks. The quality of annotations tends to deteriorate with the transitio…
View article: Learning from Noisy Labels via Self-Taught On-the-Fly Meta Loss Rescaling
Learning from Noisy Labels via Self-Taught On-the-Fly Meta Loss Rescaling Open
Correct labels are indispensable for training effective machine learning models. However, creating high-quality labels is expensive, and even professionally labeled data contains errors and ambiguities. Filtering and denoising can be appli…
View article: Local Topology Measures of Contextual Language Model Latent Spaces With Applications to Dialogue Term Extraction
Local Topology Measures of Contextual Language Model Latent Spaces With Applications to Dialogue Term Extraction Open
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 has two shortcomings. First, such methods consider single in…
View article: Infusing Emotions into Task-oriented Dialogue Systems: Understanding, Management, and Generation
Infusing Emotions into Task-oriented Dialogue Systems: Understanding, Management, and Generation Open
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 works have explored user emotions or similar concepts in som…
View article: Dialogue Ontology Relation Extraction via Constrained Chain-of-Thought Decoding
Dialogue Ontology Relation Extraction via Constrained Chain-of-Thought Decoding Open
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 customer service recordings, comes without ontology and annotation…
View article: Learning With an Open Horizon in Ever-Changing Dialogue Circumstances
Learning With an Open Horizon in Ever-Changing Dialogue Circumstances Open
Task-oriented dialogue systems aid users in achieving their goals for specific tasks, e.g., booking a hotel room or managing a schedule. The systems experience various changes during their lifetime such as new tasks emerging or varying use…
View article: A Confidence-based Acquisition Model for Self-supervised Active Learning and Label Correction
A Confidence-based Acquisition Model for Self-supervised Active Learning and Label Correction Open
Supervised neural approaches are hindered by their dependence on large, meticulously annotated datasets, a requirement that is particularly cumbersome for sequential tasks. The quality of annotations tends to deteriorate with the transitio…
View article: From Chatter to Matter: Addressing Critical Steps of Emotion Recognition Learning in Task-oriented Dialogue
From Chatter to Matter: Addressing Critical Steps of Emotion Recognition Learning in Task-oriented Dialogue Open
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 dialogues, the task-oriented counterpart is largely left unattende…
View article: EmoUS: Simulating User Emotions in Task-Oriented Dialogues
EmoUS: Simulating User Emotions in Task-Oriented Dialogues Open
Existing user simulators (USs) for task-oriented dialogue systems only model\nuser behaviour on semantic and natural language levels without considering the\nuser persona and emotions. Optimising dialogue systems with generic user\npolicie…
View article: ChatGPT for Zero-shot Dialogue State Tracking: A Solution or an Opportunity?
ChatGPT for Zero-shot Dialogue State Tracking: A Solution or an Opportunity? Open
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 aggressive data augmentation and fine-tuning of ever larger …
View article: ConvLab-3: A Flexible Dialogue System Toolkit Based on a Unified Data Format
ConvLab-3: A Flexible Dialogue System Toolkit Based on a Unified Data Format Open
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. Proceedings of the 2023 Conference on E…
View article: From Chatter to Matter: Addressing Critical Steps of Emotion Recognition Learning in Task-oriented Dialogue
From Chatter to Matter: Addressing Critical Steps of Emotion Recognition Learning in Task-oriented Dialogue Open
Shutong Feng, Nurul Lubis, Benjamin Ruppik, Christian Geishauser, Michael Heck, Hsien-chin Lin, Carel van Niekerk, Renato Vukovic, Milica Gasic. Proceedings of the 24th Meeting of the Special Interest Group on Discourse and Dialogue. 2023.
View article: ChatGPT for Zero-shot Dialogue State Tracking: A Solution or an Opportunity?
ChatGPT for Zero-shot Dialogue State Tracking: A Solution or an Opportunity? Open
Michael Heck, Nurul Lubis, Benjamin Ruppik, Renato Vukovic, Shutong Feng, Christian Geishauser, Hsien-chin Lin, Carel van Niekerk, Milica Gasic. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volum…
View article: ConvLab-3: A Flexible Dialogue System Toolkit Based on a Unified Data Format
ConvLab-3: A Flexible Dialogue System Toolkit Based on a Unified Data Format Open
Task-oriented dialogue (TOD) systems function as digital assistants, guiding users through various tasks such as booking flights or finding restaurants. Existing toolkits for building TOD systems often fall short of in delivering comprehen…
View article: Dialogue Evaluation with Offline Reinforcement Learning
Dialogue Evaluation with Offline Reinforcement Learning Open
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 every iteration of the development phase. Simulated users c…
View article: GenTUS: Simulating User Behaviour and Language in Task-oriented Dialogues with Generative Transformers
GenTUS: Simulating User Behaviour and Language in Task-oriented Dialogues with Generative Transformers Open
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, but there is still a gap from semantic actions to natural…
View article: Dialogue Term Extraction using Transfer Learning and Topological Data Analysis
Dialogue Term Extraction using Transfer Learning and Topological Data Analysis Open
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, slots, and values. As we move towards adaptable dialogue s…
View article: EmoWOZ: A Large-Scale Corpus and Labelling Scheme for Emotion Recognition in Task-Oriented Dialogue Systems
EmoWOZ: A Large-Scale Corpus and Labelling Scheme for Emotion Recognition in Task-Oriented Dialogue Systems Open
This is the dataset created for the paper, "EmoWOZ: A Large-Scale Corpus and Labelling Scheme for Emotion Recognition in Task-Oriented Dialogue Systems" (https://arxiv.org/abs/2109.04919).\n\nEmoWOZ is based on MultiWOZ, a multi-domain tas…
View article: EmoWOZ: A Large-Scale Corpus and Labelling Scheme for Emotion Recognition in Task-Oriented Dialogue Systems
EmoWOZ: A Large-Scale Corpus and Labelling Scheme for Emotion Recognition in Task-Oriented Dialogue Systems Open
This is the dataset created for the paper, "EmoWOZ: A Large-Scale Corpus and Labelling Scheme for Emotion Recognition in Task-Oriented Dialogue Systems" (https://arxiv.org/abs/2109.04919). EmoWOZ is based on MultiWOZ, a multi-domain task-o…
View article: Dynamic Dialogue Policy for Continual Reinforcement Learning
Dynamic Dialogue Policy for Continual Reinforcement Learning Open
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 and tasks, a task-oriented dialogue system must have the capa…
View article: Robust Dialogue State Tracking with Weak Supervision and Sparse Data
Robust Dialogue State Tracking with Weak Supervision and Sparse Data Open
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 sparsity, distributional shift and the occurrence of new concepts …
View article: EmoWOZ: A Large-Scale Corpus and Labelling Scheme for Emotion Recognition in Task-Oriented Dialogue Systems
EmoWOZ: A Large-Scale Corpus and Labelling Scheme for Emotion Recognition in Task-Oriented Dialogue Systems Open
This is the dataset created for the paper, "EmoWOZ: A Large-Scale Corpus and Labelling Scheme for Emotion Recognition in Task-Oriented Dialogue Systems" (https://arxiv.org/abs/2109.04919).\n\nEmoWOZ is based on MultiWOZ, a multi-domain tas…
View article: Robust Dialogue State Tracking with Weak Supervision and Sparse Data
Robust Dialogue State Tracking with Weak Supervision and Sparse Data Open
Generalizing dialogue state tracking (DST) to new data is especially challenging due to the strong reliance on abundant and fine-grained supervision during training. Sample sparsity, distributional shift, and the occurrence of new concepts…
View article: GenTUS: Simulating User Behaviour and Language in Task-oriented Dialogues with Generative Transformers
GenTUS: Simulating User Behaviour and Language in Task-oriented Dialogues with Generative Transformers Open
Hsien-chin Lin, Christian Geishauser, Shutong Feng, Nurul Lubis, Carel van Niekerk, Michael Heck, Milica Gasic. Proceedings of the 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue. 2022.
View article: Dialogue Term Extraction using Transfer Learning and Topological Data Analysis
Dialogue Term Extraction using Transfer Learning and Topological Data Analysis Open
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, slots and values. As we move towards adaptable dialogue sy…
View article: Dialogue Evaluation with Offline Reinforcement Learning
Dialogue Evaluation with Offline Reinforcement Learning Open
Nurul Lubis, Christian Geishauser, Hsien-chin Lin, Carel van Niekerk, Michael Heck, Shutong Feng, Milica Gasic. Proceedings of the 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue. 2022.