Belief Augmented Frame Sets for Knowledge Representation in Spoken Dialog Systems
نویسندگان
چکیده
We propose a frame structure that is augmented with belief functions to model knowledge in a spoken dialog system. In addition we propose methods to combine belief functions in the network, and operations on the network to support a dialog manager. We show how our Belief Augmented Frames framework can be used to manage a spoken dialog system, and give a simple example on how knowledge can be represented and integrated.
منابع مشابه
A Frame-Based Probabilistic Framework for Spoken Dialog Management Using Dialog Examples
This paper proposes a probabilistic framework for spoken dialog management using dialog examples. To overcome the complexity problems of the classic partially observable Markov decision processes (POMDPs) based dialog manager, we use a frame-based belief state representation that reduces the complexity of belief update. We also used dialog examples to maintain a reasonable number of system acti...
متن کاملHybrid Dialog State Tracker with ASR Features
This paper presents a hybrid dialog state tracker enhanced by trainable Spoken Language Understanding (SLU) for slotfilling dialog systems. Our architecture is inspired by previously proposed neuralnetwork-based belief-tracking systems. In addition we extended some parts of our modular architecture with differentiable rules to allow end-to-end training. We hypothesize that these rules allow our...
متن کاملUbiquitous Knowledge Modeling for Dialogue Systems
The main general problem that we want to address is the reconfiguration of dialogue systems to work with a generic plug-and-play device. This paper describes our research in designing knowledge-based everyday devices that can be dynamically adapted to spoken dialogue systems. We propose a model for ubiquitous knowledge representation that enables the spoken dialogue system to be aware of the de...
متن کاملProbabilistic Ontology Trees for Belief Tracking in Dialog Systems
We introduce a novel approach for robust belief tracking of user intention within a spoken dialog system. The space of user intentions is modeled by a probabilistic extension of the underlying domain ontology called a probabilistic ontology tree (POT). POTs embody a principled approach to leverage the dependencies among domain concepts and incorporate corroborating or conflicting dialog observa...
متن کاملA Statistical Spoken Dialogue System using Complex User Goals and Value Directed Compression
This paper presents the first demonstration of a statistical spoken dialogue system that uses automatic belief compression to reason over complex user goal sets. Reasoning over the power set of possible user goals allows complex sets of user goals to be represented, which leads to more natural dialogues. The use of the power set results in a massive expansion in the number of belief states main...
متن کامل