首页> 外文会议>Human interface and the management of information >Using Graphical Models for an Intelligent Mixed-Initiative Dialog Management System
【24h】

Using Graphical Models for an Intelligent Mixed-Initiative Dialog Management System

机译:将图形模型用于智能混合启动对话框管理系统

获取原文
获取原文并翻译 | 示例

摘要

The main goal of dialog management is to provide all information needed to perform e. g. a SQL-query, a navigation task, etc. Two principal approaches for dialog management systems exist: system directed ones and mixed-initiative ones. In this paper, we combine both approaches mentioned above in a novel way, and address the problem of natural intuitive dialog management. The objective of our approach is to provide a natural dialog flow. The whole dialog is therefore represented in a finite state machine: the information gathered during the dialog is represented in the states of the finite state machine; the transitions within the state machine denote the dialog steps into which the dialog is separated. The information is obtained from each natural spoken sentence by hierarchical decoding into tags, e. g. the name-tag and the address-tag. These information tags are gathered during the dialog; either by human initiative or by distinct questioning by the dialog manager. The models use information from the semantic information tags, the dialog history, and the training corpus. From all these integrated parts we achieve the best path to the end of the dialog by Viterbi decoding through the transition network after each information step. From the Air Travel Information System (ATIS) database, we extract all 21650 naturally spoken questions and the SQL-queries as answers for the trainings phase. The experiments have been realized on 200 automatically generated dialog sentences. The system obtains the semantic information in all test-sentences and leads the dialogs successfully to the end. In 66.5% of the sample dialogs we achieve the minimum of the required dialog steps. Hence, 33.5% of the dialogs have over-length.
机译:对话管理的主要目标是提供执行e所需的所有信息。 G。 SQL查询,导航任务等。对话框管理系统的两种主要方法是:系统指导的方法和混合启动的方法。在本文中,我们以一种新颖的方式结合了上述两种方法,并解决了自然直观对话管理的问题。我们方法的目的是提供自然的对话流程。因此,整个对话框在有限状态机中表示:在对话框期间收集的信息以有限状态机的状态表示;状态机内的转换表示将对话框分为多个对话框的步骤。通过分层解码成例如标签的标签,从每个自然口语句子获得该信息。 G。名称标签和地址标签。这些信息标签是在对话期间收集的。要么是人为主动,要么是对话管理者提出了独特的疑问。这些模型使用来自语义信息标签,对话历史记录和训练语料库的信息。通过所有这些集成的部分,我们在每个信息步骤之后通过过渡网络进行维特比解码,从而获得通向对话结尾的最佳路径。从航空旅行信息系统(ATIS)数据库中,我们提取所有21650个自然口语问题和SQL查询作为培训阶段的答案。实验已经在200个自动生成的对话语句上实现。系统获得所有测试语句中的语义信息,并将对话成功地引导到最后。在66.5%的示例对话框中,我们实现了所需的最少对话步骤。因此,有33.5%的对话框过长。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号