Related papers: Dynamic Schema Graph Fusion Network for Multi-Doma…
Dialogue State Tracking (DST) is an essential element of conversational AI with the objective of deeply understanding the conversation context and leading it toward answering user requests. Due to high demands for open-domain and multi-turn…
Modeling user preference from his historical sequences is one of the core problems of sequential recommendation. Existing methods in this field are widely distributed from conventional methods to deep learning methods. However, most of them…
Semantic parsing has long been a fundamental problem in natural language processing. Recently, cross-domain context-dependent semantic parsing has become a new focus of research. Central to the problem is the challenge of leveraging…
The medical dialogue system is a promising application that can provide great convenience for patients. The dialogue state tracking (DST) module in the medical dialogue system which interprets utterances into the machine-readable structure…
Zero/few-shot transfer to unseen services is a critical challenge in task-oriented dialogue research. The Schema-Guided Dialogue (SGD) dataset introduced a paradigm for enabling models to support any service in zero-shot through schemas,…
Modeling and predicting temporal point processes (TPPs) is critical in domains such as neuroscience, epidemiology, finance, and social sciences. We introduce the Spiking Dynamic Graph Network (SDGN), a novel framework that leverages the…
We present a generic framework for spatio-temporal (ST) data modeling, analysis, and forecasting, with a special focus on data that is sparse in both space and time. Our multi-scaled framework is a seamless coupling of two major components:…
Accurate traffic flow prediction is essential for applications like transport logistics but remains challenging due to complex spatio-temporal correlations and non-linear traffic patterns. Existing methods often model spatial and temporal…
Traffic forecasting is important in intelligent transportation systems of webs and beneficial to traffic safety, yet is very challenging because of the complex and dynamic spatio-temporal dependencies in real-world traffic systems. Prior…
Effective congestion management along signalized corridors is essential for improving productivity and reducing costs, with arterial travel time serving as a key performance metric. Traditional approaches, such as Coordinated Signal Timing…
Deep learning-based crowd counting methods have achieved remarkable progress in recent years. However, in complex crowd scenarios, existing models still face challenges when adapting to significant density distribution differences between…
Discrete-Time Dynamic Graphs (DTDGs), which are prevalent in real-world implementations and notable for their ease of data acquisition, have garnered considerable attention from both academic researchers and industry practitioners. The…
Tracking dialogue states to better interpret user goals and feed downstream policy learning is a bottleneck in dialogue management. Common practice has been to treat it as a problem of classifying dialogue content into a set of pre-defined…
Recent progress in research on Deep Graph Networks (DGNs) has led to a maturation of the domain of learning on graphs. Despite the growth of this research field, there are still important challenges that are yet unsolved. Specifically,…
Graph Domain Adaptation (GDA) aims to bridge distribution shifts between domains by transferring knowledge from well-labeled source graphs to given unlabeled target graphs. One promising recent approach addresses graph transfer by…
We present a new approach to dialogue management using conversational knowledge graphs as core representation of the dialogue state. To this end, we introduce a new dataset, GraphWOZ, which comprises Wizard-of-Oz dialogues in which human…
Dynamic Scene Graph Generation (DSGG) models how object relations evolve over time in videos. However, existing methods are trained only on annotated object pairs and lack guidance for non-related pairs, making it difficult to identify…
Schema-guided dialogue state trackers can generalise to new domains without further training, yet they are sensitive to the writing style of the schemata. Augmenting the training set with human or synthetic schema paraphrases improves the…
Semantic Machines (SM) have introduced the use of the dataflow (DF) paradigm to dialogue modelling, using computational graphs to hierarchically represent user requests, data, and the dialogue history [Semantic Machines et al. 2020].…
Previous zero-shot dialogue state tracking (DST) methods only apply transfer learning, ignoring unlabelled data in the target domain. We transform zero-shot DST into few-shot DST by utilising such unlabelled data via joint and self-training…