RavenClaw介绍_003

1 - Introduction - 介绍

Dialog management maintains continuity over turns in a conversation between human and computer.

对话管理在人类与计算机之间的对话的回合中保持连续性。

While many approaches have been developed to address this problem, we believe that the essence of dialog management resides in performing two functions: interpreting user inputs with respect to task(s) within the domain, and maintaining the coherence, over time, of the conversation.

虽然已开发了多种方法来解决此问题，但我们相信对话管理的核心在于执行两个功能：根据领域内的任务解释用户输入，以及随时间保持对话的连贯性。

---

Task structure is not always explicitly represented in dialog systems.

Task结构在对话系统中并不总是明确表示的。

For example, in graph-based systems (“IVR” systems) task structure is implicit in the structure of the graph.

例如，在基于图形的系统（“交互式语音应答”系统）中，task结构是隐含在图形的结构中的。

In information access systems, the “task” consists of form filling and is again implicitly represented in the architecture.

在信息访问系统中，“任务”包括“表单填写”，并且同样隐含在架构中。

Explicit task representations, however, are necessary for more complex domains, for example travel planning.

然而，对于更复杂的领域，例如旅行规划，显式的任务表示是必要的。

The CMU Agenda dialog manager [^1] represents one approach to directly modeling the human’s task.

CMU Agenda 对话管理器[^1]表示一种直接模拟人类任务的方法。

参考文献如下注释

Xu, W. and Rudnicky, A.,

“Task-based Dialog Management Using an Agenda”,

ANLP/NAACL 2000

Workshop on Conversational Systems, May 2000.

徐伟 和 鲁德尼基（A Rudnicky），

“使用议程的任务型对话管理”，

ANLP/NAACL 2000

对话系统研讨会，2000年5月。

---

The current RavenClaw dialog manager builds on the experience of Agenda, notably in providing a clear separation between task-specific behavior and more general discourse behaviors (which we refer to as “conversational strategies”).

当前的 RavenClaw 对话管理器建立在Agenda 的经验之上，特别是在提供任务特定行为和更一般的对话行为（我们称之为“对话策略”）之间的明确分离方面。

The system development and maintenance effort is entirely focused on providing a description of the task to be performed; the mechanisms for maintaining the coherence and continuity of the conversation are generated by an underlying dialog engine.

系统开发和维护工作完全集中在提供要执行的任务描述上；维护对话连贯性和连续性的机制由底层的对话引擎生成。

---

Section 2 describes in detail the structure, mechanisms and functionality of the RavenClaw architecture.

第2节详细描述了RavenClaw架构的结构、机制和功能。

Subsequently, Section 3 summarizes our experience in using it in five different applications that span a variety of task types.

随后，第3节总结了我们在五种不同的应用程序中使用它的经验，这些应用程序涵盖了各种任务类型。

Finally, Section 4 concludes the paper and presents our current and future plans for extending this framework.

最后，第4节总结了本文，并介绍了我们当前和未来的计划，以扩展此框架。