170 citations · 405 across the 18 of their papers we have counts for
23 papers
Leveraging Low-Level Symbolic Competences for Unsupervised Grounding in Hallucination Detection
Renato Vukovic, Hsien-chin Lin, Carel van Niekerk +5
Hallucination-where a language model generates outputs that are factually incorrect or unsupported by the source-is a major challenge for both prompted and fine-tuned language mode…
Exploration Through Introspection: A Self-Aware Reward Model
Michael Petrowski, Milica Gašić
Understanding how artificial agents model internal mental states is central to advancing Theory of Mind in AI. Evidence points to a unified system for self- and other-awareness. We…
Text-to-SQL Task-oriented Dialogue Ontology Construction
Renato Vukovic, Carel van Niekerk, Michael Heck +5
Large language models (LLMs) are widely used as general-purpose knowledge sources, but they rely on parametric knowledge, limiting explainability and trustworthiness. In task-orien…
Learning from Noisy Labels via Self-Taught On-the-Fly Meta Loss Rescaling
Michael Heck, Christian Geishauser, Nurul Lubis +6
Correct labels are indispensable for training effective machine learning models. However, creating high-quality labels is expensive, and even professionally labeled data contains e…
Speech-based Slot Filling using Large Language Models
Guangzhi Sun, Shutong Feng, Dongcheng Jiang +3
Recently, advancements in large language models (LLMs) have shown an unprecedented ability across various language tasks. This paper investigates the potential application of LLMs…
Topology of Word Embeddings: Singularities Reflect Polysemy
Alexander Jakubowski, Milica Gašić, Marcus Zibrowius
The manifold hypothesis suggests that word vectors live on a submanifold within their ambient vector space. We argue that we should, more accurately, expect them to live on a pinch…
Tree-Structured Semantic Encoder with Knowledge Sharing for Domain Adaptation in Natural Language Generation
Bo-Hsiang Tseng, Paweł Budzianowski, Yen-Chen Wu +1
Domain adaptation in natural language generation (NLG) remains challenging because of the high complexity of input semantics across domains and limited data of a target domain. Thi…
AgentGraph: Towards Universal Dialogue Management with Structured Deep Reinforcement Learning
Lu Chen, Zhi Chen, Bowen Tan +3
Dialogue policy plays an important role in task-oriented spoken dialogue systems. It determines how to respond to users. The recently proposed deep reinforcement learning (DRL) app…
Addressing Objects and Their Relations: The Conversational Entity Dialogue Model
Stefan Ultes, Paweł Budzianowski, Iñigo Casanueva +5
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.,…
Deep learning for language understanding of mental health concepts derived from Cognitive Behavioural Therapy
Lina Rojas-Barahona, Bo-Hsiang Tseng, Yinpei Dai +5
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,…
Nearly Zero-Shot Learning for Semantic Decoding in Spoken Dialogue Systems
Lina M. Rojas-Barahona, Stefan Ultes, Pawel Budzianowski +4
This paper presents two ways of dealing with scarce data in semantic decoding using N-Best speech recognition hypotheses. First, we learn features by using a deep learning architec…
Feudal Reinforcement Learning for Dialogue Management in Large Domains
Iñigo Casanueva, Paweł Budzianowski, Pei-Hao Su +4
Reinforcement learning (RL) is a promising approach to solve dialogue policy optimisation. Traditional RL algorithms, however, fail to scale to large domains due to the curse of di…
Sample Efficient Deep Reinforcement Learning for Dialogue Systems with Large Action Spaces
Gellért Weisz, Paweł Budzianowski, Pei-Hao Su +1
In spoken dialogue systems, we aim to deploy artificial intelligence to build automated dialogue agents that can converse with humans. A part of this effort is the policy optimisat…
Reward-Balancing for Statistical Spoken Dialogue Systems using Multi-objective Reinforcement Learning
Stefan Ultes, Paweł Budzianowski, Iñigo Casanueva +6
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 dialo…
Sub-domain Modelling for Dialogue Management with Hierarchical Reinforcement Learning
Paweł Budzianowski, Stefan Ultes, Pei-Hao Su +5
Human conversation is inherently complex, often spanning many different topics/domains. This makes policy learning for dialogue systems very challenging. Standard flat reinforcemen…
Exploiting Sentence and Context Representations in Deep Neural Models for Spoken Language Understanding
Lina M. Rojas Barahona, Milica Gasic, Nikola Mrkšić +4
This paper presents a deep learning architecture for the semantic decoder component of a Statistical Spoken Dialogue System. In a slot-filling dialogue, the semantic decoder predic…
Dialogue manager domain adaptation using Gaussian process reinforcement learning
Milica Gasic, Nikola Mrksic, Lina M. Rojas-Barahona +5
Spoken dialogue systems allow humans to interact with machines using natural speech. As such, they have many benefits. By using speech as the primary communication medium, a comput…
Conditional Generation and Snapshot Learning in Neural Dialogue Systems
Tsung-Hsien Wen, Milica Gasic, Nikola Mrksic +5
Recently a variety of LSTM-based conditional language models (LM) have been applied across a range of language generation tasks. In this work we study various model architectures a…
Continuously Learning Neural Dialogue Management
Pei-Hao Su, Milica Gasic, Nikola Mrksic +5
We describe a two-step approach for dialogue management in task-oriented spoken dialogue systems. A unified neural network framework is proposed to enable the system to first learn…
On-line Active Reward Learning for Policy Optimisation in Spoken Dialogue Systems
Pei-Hao Su, Milica Gasic, Nikola Mrksic +5
The ability to compute an accurate reward function is essential for optimising a dialogue policy via reinforcement learning. In real-world applications, using explicit user feedbac…
A Network-based End-to-End Trainable Task-oriented Dialogue System
Tsung-Hsien Wen, David Vandyke, Nikola Mrksic +5
Teaching machines to accomplish tasks by conversing naturally with humans is challenging. Currently, developing task-oriented dialogue systems requires creating multiple components…
Multi-domain Neural Network Language Generation for Spoken Dialogue Systems
Tsung-Hsien Wen, Milica Gasic, Nikola Mrksic +4
Moving from limited-domain natural language generation (NLG) to open domain is difficult because the number of semantic input combinations grows exponentially with the number of do…
Counter-fitting Word Vectors to Linguistic Constraints
Nikola Mrkšić, Diarmuid Ó Séaghdha, Blaise Thomson +6
In this work, we present a novel counter-fitting method which injects antonymy and synonymy constraints into vector space representations in order to improve the vectors' capabilit…