Search Results for author:
Found 37 papers, 9 papers with code
Learning from Noisy Labels via Self-Taught On-the-Fly Meta Loss Rescaling
However, creating high-quality labels is expensive, and even professionally labeled data contains errors and ambiguities.
Local Topology Measures of Contextual Language Model Latent Spaces With Applications to Dialogue Term Extraction
Second, the high performance of these models relies on fine-tuning the embedding model in conjunction with the classifier, which may not always be feasible due to the size or inaccessibility of the underlying feature-generation model.
Infusing Emotions into Task-oriented Dialogue Systems: Understanding, Management, and Generation
Emotions are indispensable in human communication, but are often overlooked in task-oriented dialogue (ToD) modelling, where the task success is the primary focus.
Speech-based Slot Filling using Large Language Models
Recently, advancements in large language models (LLMs) have shown an unprecedented ability across various language tasks.
A Confidence-based Acquisition Model for Self-supervised Active Learning and Label Correction
Furthermore, the data corrections suggested by our method contribute to an overall improvement in the quality of the resulting datasets.
Affect Recognition in Conversations Using Large Language Models
Affect recognition, encompassing emotions, moods, and feelings, plays a pivotal role in human communication.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
From Chatter to Matter: Addressing Critical Steps of Emotion Recognition Learning in Task-oriented Dialogue
Our framework yields significant improvements for a range of chit-chat ERC models on EmoWOZ, a large-scale dataset for user emotion in ToDs.
ChatGPT for Zero-shot Dialogue State Tracking: A Solution or an Opportunity?
Recent research on dialogue state tracking (DST) focuses on methods that allow few- and zero-shot transfer to new domains or schemas.
EmoUS: Simulating User Emotions in Task-Oriented Dialogues
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 emotions.
ConvLab-3: A Flexible Dialogue System Toolkit Based on a Unified Data Format
Task-oriented dialogue (TOD) systems function as digital assistants, guiding users through various tasks such as booking flights or finding restaurants.
Dialogue Evaluation with Offline Reinforcement Learning
They are ideally evaluated with human users, which however is unattainable to do at every iteration of the development phase.
GenTUS: Simulating User Behaviour and Language in Task-oriented Dialogues with Generative Transformers
In addition, its behaviour can be further shaped with reinforcement learning opening the door to training specialised user simulators.
Dialogue Term Extraction using Transfer Learning and Topological Data Analysis
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.
Dynamic Dialogue Policy for Continual Reinforcement Learning
The lack of a framework with training protocols, baseline models and suitable metrics, has so far hindered research in this direction.
Robust Dialogue State Tracking with Weak Supervision and Sparse Data
Our architecture and training strategies improve robustness towards sample sparsity, new concepts and topics, leading to state-of-the-art performance on a range of benchmarks.
What Does The User Want? Information Gain for Hierarchical Dialogue Policy Optimisation
The dialogue management component of a task-oriented dialogue system is typically optimised via reinforcement learning (RL).
EmoWOZ: A Large-Scale Corpus and Labelling Scheme for Emotion Recognition in Task-Oriented Dialogue Systems
We report a set of experimental results to show the usability of this corpus for emotion recognition and state tracking in task-oriented dialogues.
Ranked #1 on
Emotion Recognition in Conversation
on EmoWoz
Emotion Recognition in Conversation
Task-Oriented Dialogue Systems
Uncertainty Measures in Neural Belief Tracking and the Effects on Dialogue Policy Performance
This highlights the importance of developing neural dialogue belief trackers that take uncertainty into account.
Domain-independent User Simulation with Transformers for Task-oriented Dialogue Systems
TUS can compete with rule-based user simulators on pre-defined domains and is able to generalise to unseen domains in a zero-shot fashion.
Out-of-Task Training for Dialog State Tracking Models
Dialog state tracking (DST) suffers from severe data sparsity.
LAVA: Latent Action Spaces via Variational Auto-encoding for Dialogue Policy Optimization
In this paper, we explore three ways of leveraging an auxiliary task to shape the latent variable distribution: via pre-training, to obtain an informed prior, and via multitask learning.
Topology of Word Embeddings: Singularities Reflect Polysemy
We argue that we should, more accurately, expect them to live on a pinched manifold: a singular quotient of a manifold obtained by identifying some of its points.
Knowing What You Know: Calibrating Dialogue Belief State Distributions via Ensembles
The ability to accurately track what happens during a conversation is essential for the performance of a dialogue system.
TripPy: A Triple Copy Strategy for Value Independent Neural Dialog State Tracking
In this paper we present a new approach to DST which makes use of various copy mechanisms to fill slots with values.
Ranked #11 on
Multi-domain Dialogue State Tracking
on MULTIWOZ 2.1
dialog state tracking
Multi-domain Dialogue State Tracking
+2
Tree-Structured Semantic Encoder with Knowledge Sharing for Domain Adaptation in Natural Language Generation
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.
Addressing Objects and Their Relations: The Conversational Entity Dialogue Model
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., relations.
MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling
Even though machine learning has become the major scene in dialogue research community, the real breakthrough has been blocked by the scale of data available.
Large-Scale Multi-Domain Belief Tracking with Knowledge Sharing
Robust dialogue belief tracking is a key component in maintaining good quality dialogue systems.
Ranked #22 on
Multi-domain Dialogue State Tracking
on MULTIWOZ 2.0
Feudal Reinforcement Learning for Dialogue Management in Large Domains
Reinforcement learning (RL) is a promising approach to solve dialogue policy optimisation.
Sample Efficient Deep Reinforcement Learning for Dialogue Systems with Large Action Spaces
A part of this effort is the policy optimisation task, which attempts to find a policy describing how to respond to humans, in the form of a function taking the current state of the dialogue and returning the response of the system.
Uncertainty Estimates for Efficient Neural Network-based Dialogue Policy Optimisation
This paper examines approaches to extract uncertainty estimates from deep Q-networks (DQN) in the context of dialogue management.
A Benchmarking Environment for Reinforcement Learning Based Task Oriented Dialogue Management
Dialogue assistants are rapidly becoming an indispensable daily aid.
Reward-Balancing for Statistical Spoken Dialogue Systems using Multi-objective Reinforcement Learning
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 dialogue length.
Multi-Objective Reinforcement Learning
reinforcement-learning
+2
Sub-domain Modelling for Dialogue Management with Hierarchical Reinforcement Learning
In doing that, we show that our approach has the potential to facilitate policy optimisation for more sophisticated multi-domain dialogue systems.
Semantic Specialisation of Distributional Word Vector Spaces using Monolingual and Cross-Lingual Constraints
We present Attract-Repel, an algorithm for improving the semantic quality of word vectors by injecting constraints extracted from lexical resources.
Counter-fitting Word Vectors to Linguistic Constraints
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' capability for judging semantic similarity.
Multi-domain Dialog State Tracking using Recurrent Neural Networks
Dialog state tracking is a key component of many modern dialog systems, most of which are designed with a single, well-defined domain in mind.
