Integrating linguistic and domain knowledge for spoken dialogue systems in multiple domains
Integrating linguistic and domain knowledge for spoken dialogue systems in multiple domains
复制标题
整合多个领域口语对话系统的语言和领域知识
DOI：
--
复制
发表时间：
2003
期刊：
影响因子：
--
通讯作者：
Mary D. Swift
中科院分区：
文献类型：
--
作者：
M. Dzikovska;James F. Allen;Mary D. Swift
在多个领域中开发口语对话系统的一个挑战是使用共享领域本体来促进系统组件通信。由于每个域都有自己的一组与应用程序相关的概念和操作，因此使系统适应新的域需要定制组件以使用该域所需的本体表示。我们在多领域开发方面的研究突出了通用语言界面和特定于任务的推理应用程序的本体需求的差异。尽管不同的领域应用程序有它们自己的本体，但是跨域的口头对话交互的许多方面是共同的。在本文中，我们提出了一种新的方法，通过维护两个本体，一个是为语言表示而通用的，另一个是为领域定制的，并定义了它们之间的映射，从而将一个广泛覆盖的解析器定制到不同的领域。通过这种方式，我们保留了跨域的广泛覆盖的语言组件，并产生了最适合领域推理器的语义表示。
One challenge for developing spoken dialogue systems in multiple domains is facilitating system component communication using a shared domain ontology. Since each domain comes with its own set of concepts and actions relevant to the application, adapting a system to a new domain requires customizing components to use the ontological representations required for that domain. Our research in multiple domain development has highlighted differences in the ontological needs of a generalpurpose language interface and a task-specific reasoning application. Although different domain applications have their own ontologies, many aspects of spoken dialogue interaction are common across domains. In this paper, we present a new method of customizing a broad-coverage parser to different domains by maintaining two ontologies, one that is generalized for language representation, and another that is customized to the domain, and defining mappings between them. In this way we preserve the broad-coverage language components across domains as well as produce semantic representations that are optimally suited to the domain reasoners.