首页> 外文会议>Conference on Speech Technology and Human-Computer Dialogue >GENERIC ARCHITECTURE FOR NATURAL LANGUAGE GENERATION IN SPOKEN HUMAN-COMPUTER DIALOGUE
【24h】

GENERIC ARCHITECTURE FOR NATURAL LANGUAGE GENERATION IN SPOKEN HUMAN-COMPUTER DIALOGUE

机译:用于口语人类对话中的自然语言生成的通用架构

获取原文

摘要

The human-computer dialogue field is nowadays a rather developed technology and research branch in its own right, but consensus had not been reached yet with respect to several issues. Out of these, several aspects related to answer generation in spoken natural language are addressed in this paper. First, a modular architecture integrated into a distributed, agent-based dialogue framework and in compliance with existing standard architectures for natural language generation is specified. Its strengths and weaknesses regarding existing approaches and in the context of human-computer spoken dialogue are emphasized. Second, the interfaces between modules in the architecture are presented in detail; information representation issues, involving XML grammars, are pointed out. Then, there are provided several examples of knowledge representation, in XML format, for the information exchanged between the modules in the architecture. Finally, comparisons with similar work and a set of conclusions are provided.
机译:现在,人机对话领域是一个相当开发的技术和研究分支,但尚未达成共识,但尚未达成若干问题。在这些方面,在本文中解决了与口语自然语言中的答案产生相关的几个方面。首先,将模块化架构集成到分布式的基于代理的对话框框架和符合现有的自然语言生成标准体系结构中。强调了其关于现有方法和在人机口语对话的背景下的优势和缺点。其次,详细介绍了架构中模块之间的接口;指出了涉及XML语法的信息表示问题。然后,提供若干知识表示的示例,以XML格式,用于在架构中的模块之间交换的信息。最后,提供了与类似工作的比较和一系列结论。

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