• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>User modeling and user-adapted interaction >A System for Building Intelligent Agents that Learn to Retrieve and Extract Information
【24h】

A System for Building Intelligent Agents that Learn to Retrieve and Extract Information

机译：一种用于学习检索和提取信息的智能代理的系统

获取原文
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

We present a system for rapidly and easily building instructable and self-adaptive software agents that retrieve and extract information. Our Wisconsin Adaptive Web Assistant (W_(WAW)) constructs intelligent agents by accepting user preferences in the form of instructions. These user-provided instructions are compiled into neural networks that are responsible for the adaptive capabilities of an intelligent agent. The agent's neural networks are modified via user-provided and system-constructed training examples. Users can create training examples by rating Web pages (or documents), but more importantly W_(waw)'S agents uses techniques from reinforcement learning to internally create their own examples. Users can also provide additional instruction throughout the life of an agent. Our experimental evaluations on a 'home-page finder' agent and a 'seminar-announcement extractor' agent illustrate the value of using instructable and adaptive agents for retrieving and extracting information.
机译：我们提出了一种用于快速，轻松地构建可检索和提取信息的可指导和自适应软件代理的系统。我们的威斯康星州自适应Web助手（W_（WAW））通过接受指令形式的用户首选项来构造智能代理。这些用户提供的指令被编译到负责智能代理的自适应功能的神经网络中。代理的神经网络通过用户提供的和系统构建的训练示例进行了修改。用户可以通过对网页（或文档）进行评级来创建培训示例，但更重要的是，W_（waw）的代理使用强化学习中的技术在内部创建自己的示例。用户还可以在代理的整个生命周期内提供其他说明。我们对“首页查找器”代理和“研讨会通知提取器”代理的实验评估说明了使用可指导和自适应的代理来检索和提取信息的价值。

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