Related papers: MultiWOZ 2.4: A Multi-Domain Task-Oriented Dialogu…

Evaluation is crucial in the development process of task-oriented dialogue systems. As an evaluation method, user simulation allows us to tackle issues such as scalability and cost-efficiency, making it a viable choice for large-scale…

Task-Oriented Dialogue (TOD) systems are designed to carry out specific tasks by tracking dialogue states and generating appropriate responses to help users achieve defined goals. Recently, end-to-end dialogue models pre-trained based on…

An automated metric to evaluate dialogue quality is vital for optimizing data driven dialogue management. The common approach of relying on explicit user feedback during a conversation is intrusive and sparse. Current models to estimate…

Multimodal emotion recognition is an important research topic in artificial intelligence. Over the past few decades, researchers have made remarkable progress by increasing the dataset size and building more effective algorithms. However,…

Lack of training data presents a grand challenge to scaling out spoken language understanding (SLU) to low-resource languages. Although various data augmentation approaches have been proposed to synthesize training data in low-resource…

Achieving robust language technologies that can perform well across the world's many languages is a central goal of multilingual NLP. In this work, we take stock of and empirically analyse task performance disparities that exist between…

Despite efforts to increase the representation of disabled people in AI datasets, accessibility datasets are often annotated by crowdworkers without disability-specific expertise, leading to inconsistent or inaccurate labels. This paper…

Annotation noise is widespread in datasets, but manually revising a flawed corpus is time-consuming and error-prone. Hence, given the prior knowledge in Pre-trained Language Models and the expected uniformity across all annotations, we…

Retrieving target videos based on text descriptions is a task of great practical value and has received increasing attention over the past few years. Despite recent progress, imperfect annotations in existing video retrieval datasets have…

Dialogue data in real scenarios tend to be sparsely available, rendering data-starved end-to-end dialogue systems trained inadequately. We discover that data utilization efficiency in low-resource scenarios can be enhanced by mining…

Most prior work in dialogue modeling has been on written conversations mostly because of existing data sets. However, written dialogues are not sufficient to fully capture the nature of spoken conversations as well as the potential speech…

Few-shot dialogue state tracking (DST) with Large Language Models (LLM) relies on an effective and efficient conversation retriever to find similar in-context examples for prompt learning. Previous works use raw dialogue context as search…

The rapid progress of Large Language Models (LLMs) has empowered omni models to act as voice assistants capable of understanding spoken dialogues. These models can process multimodal inputs beyond text, such as speech and visual data,…

An automated metric to evaluate dialogue quality is vital for optimizing data driven dialogue management. The common approach of relying on explicit user feedback during a conversation is intrusive and sparse. Current models to estimate…

This paper presents a novel approach for multi-task learning of language understanding (LU) and dialogue state tracking (DST) in task-oriented dialogue systems. Multi-task training enables the sharing of the neural network layers…

Dialogue assessment plays a critical role in the development of open-domain dialogue systems. Existing work are uncapable of providing an end-to-end and human-epistemic assessment dataset, while they only provide sub-metrics like coherence…

Consistency Identification has obtained remarkable success on open-domain dialogue, which can be used for preventing inconsistent response generation. However, in contrast to the rapid development in open-domain dialogue, few efforts have…

We present a fast and scalable architecture called Explicit Modular Decomposition (EMD), in which we incorporate both classification-based and extraction-based methods and design four modules (for classification and sequence labelling) to…

Obtaining annotations for complex computer vision tasks such as object detection is an expensive and time-intense endeavor involving a large number of human workers or expert opinions. Reducing the amount of annotations required while…

Pre-trained conversation models (PCMs) have achieved promising progress in recent years. However, existing PCMs for Task-oriented dialog (TOD) are insufficient for capturing the sequential nature of the TOD-related tasks, as well as for…