RavenClaw介绍_002

RavenClaw:

Dialog Management

Using Hierarchical Task Decomposition and an Expectation Agenda

RavenClaw:

对话管理

使用层次化任务分解和期望议程

Dan Bohus

Alexander I. Rudnicky

Carnegie Mellon University,

Pittsburgh, PA, 15213

{dbohus,air}@cs.cmu.edu

Dan Bohus

Alexander I. Rudnicky

卡内基梅隆大学,

宾夕法尼亚州匹兹堡，15213

{dbohus,air}@cs.cmu.edu

Abstract - 摘要

We describe RavenClaw,

a new dialog management framework developed as a successor to the Agenda architecture[1] used in the CMU Communicator.

我们描述了RavenClaw，

一个新的对话管理框架，作为CMU Communicator中使用的Agenda架构[1]的后继者而开发。

RavenClaw introduces a clear separation between task and discourse behavior specification, and allows rapid development of dialog management components for spoken dialog systems operating in complex, goal-oriented domains.

RavenClaw在task和话语行为规范之间引入了明确的分离，并允许快速开发用于在复杂、面向目标的领域中运行的口语对话系统的对话管理组件。

快速开发对话管理组件

The system development effort is focused entirely on the specification of the dialog task, while a rich set of domain-independent conversational behaviors are transparently generated by the dialog engine.

系统开发工作完全集中在对话task的规范上，而对话引擎则透明地生成一组丰富的与领域无关的对话行为。

开发关注task规范，引擎生成对话行为

To date, RavenClaw has been applied to five different domains allowing us to draw some preliminary conclusions as to the generality of the approach.

迄今为止，RavenClaw已被应用于五个不同的领域，使我们能够得出一些关于该方法通用性的初步结论。

We briefly describe our experience in developing these systems.

我们简要地描述了我们在开发这些系统方面的经验。