Related papers: WEBDial, a Multi-domain, Multitask Statistical Dia…
While multi-party conversations are often less structured than monologues and documents, they are implicitly organized by semantic level correlations across the interactive turns, and dialogue discourse analysis can be applied to predict…
How to build and use dialogue data efficiently, and how to deploy models in different domains at scale can be two critical issues in building a task-oriented dialogue system. In this paper, we propose a novel manual-guided dialogue scheme…
As large dialogue models become commonplace in practice, the problems surrounding high compute requirements for training, inference and larger memory footprint still persists. In this work, we present AUTODIAL, a multi-task dialogue model…
RDF-based systems increasingly operate in event-driven and streaming settings, where producers and consumers exchange data as discrete units of communication rather than as freely mergeable RDF statements. As existing RDF semantics and…
The dialogue management component of a task-oriented dialogue system is typically optimised via reinforcement learning (RL). Optimisation via RL is highly susceptible to sample inefficiency and instability. The hierarchical approach called…
We describe an approach to task-oriented dialogue in which dialogue state is represented as a dataflow graph. A dialogue agent maps each user utterance to a program that extends this graph. Programs include metacomputation operators for…
The Resource Description Framework (RDF) provides a common data model for the integration of "real-time" social and sensor data streams with the Web and with each other. While there exist numerous protocols and data formats for exchanging…
We introduce doc2dial, a new dataset of goal-oriented dialogues that are grounded in the associated documents. Inspired by how the authors compose documents for guiding end users, we first construct dialogue flows based on the content…
Formalizing an RDF abstract graph model to be compatible with the RDF formal semantics has remained one of the foundational problems in the Semantic Web. In this paper, we propose a new formal graph model for RDF datasets. This model allows…
Morality in dialogue systems has raised great attention in research recently. A moral dialogue system aligned with users' values could enhance conversation engagement and user connections. In this paper, we propose a framework, MoralDial to…
Dialog is an effective way to exchange information, but subtle details and nuances are extremely important. While significant progress has paved a path to address visual dialog with algorithms, details and nuances remain a challenge.…
While automatic dialogue tutors hold great potential in making education personalized and more accessible, research on such systems has been hampered by a lack of sufficiently large and high-quality datasets. Collecting such datasets…
Building Task-Oriented Dialogue (TOD) systems that generalize across different tasks remains a challenging problem. Data-driven approaches often struggle to transfer effectively to unseen tasks. While recent schema-based TOD frameworks…
Dialog systems have achieved significant progress and have been widely used in various scenarios. The previous researches mainly focused on designing dialog generation models in a single scenario, while comprehensive abilities are required…
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) approaches have been used for policy optimization. However,…
The Big Data landscape poses challenges in managing diverse data formats, requiring efficient storage and processing for high-quality analysis. Effective metadata management is crucial for organizing, accessing, and reusing data within…
Relational databases (RDBs) are widely regarded as the gold standard for storing structured information. Consequently, predictive tasks leveraging this data format hold significant application promise. Recently, Relational Deep Learning…
In this paper, we propose a hierarchical semantic overlay network for searching heterogeneous data over wide-area networks. In this system, data are represented as RDF triples based on ontologies. Peers that have the same semantics are…
We present a new approach to dialogue specification for Virtual Personal Assistants (VPAs) based on so-called dialogue workflow graphs, with several demonstrated advantages over current ontology-based methods. Our new dialogue specification…
Training statistical dialog models in spoken dialog systems (SDS) requires large amounts of annotated data. The lack of scalable methods for data mining and annotation poses a significant hurdle for state-of-the-art statistical dialog…