首页> 外文会议>KI 2011: Advances in artificial intelligence >Human-Machine Corpus Analysis for Generation and Interaction with Spoken Dialog Systems
【24h】

Human-Machine Corpus Analysis for Generation and Interaction with Spoken Dialog Systems

机译:人机语料库分析与语音对话系统的生成和交互

获取原文
获取原文并翻译 | 示例

摘要

We describe an approach to language generation for simulated end-to-end user tests based on flexible templates constructed from a corpus. We also augment the user replies by additional features such as self-corrections and fillers. This approach is a dynamic and easy way to cover many different kinds of user utterances with realistic frequencies. Our experiments show that the generated replies are comparable in variety to the utterances of real users.
机译:我们描述了一种基于语料库构造的灵活模板的,用于模拟端到端用户测试的语言生成方法。我们还通过其他功能(如自我更正和填充)​​来增加用户答复。这种方法是一种动态简便的方法,可以用实际频率覆盖许多不同种类的用户话语。我们的实验表明,所生成的回复在种类上与真实用户的话语相当。

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