图 书 馆
必应对话模式：意图、知识和用户交互Bing Dialog Model: Intent, Knowledge and User Interaction |
|
| 课程网址: | http://videolectures.net/wsdm2011_shum_bdm/ |
| 主讲教师: | Harry Shum; Yu-Ting Kuo |
| 开课单位: | 微软公司 |
| 开课时间: | 2011-08-09 |
| 课程语种: | 英语 |
| 中文简介: |  以“十个蓝色链接”的形式表现出来的互联网搜索结果已有十年之久，已不再足以满足互联网用户的需求。许多研究表明，当用户通过蓝色链接进入常规搜索结果页面时，通常只能以“命中或失败”方式部分满足用户的需求。为了应对这一挑战，我们设计了Microsoft的决策引擎Bing，不仅可以通过蓝色链接将用户导航到登录页面，而且还可以继续与用户互动以阐明意图并促进任务完成。这个新范例的基础是Bing对话模型，该模型由三个构建块组成：一个索引系统，可以从网络上全面收集信息并系统地收集知识；一个意图模型，可以从统计学上推断出用户的意图并预测下一步的行动；以及一个交互模型，它可以引发通过对用户信息进行数学优化的Web信息和领域知识表示来实现用户意图。在本次演讲中，我将详细介绍Bing对话模型，并通过[url] 推出以来的一些创新功能在实际中进行演示。 |
| 课程简介: | The decade-old Internet search outcomes, manifested in the form of “ten blue links,” are no longer sufficient for Internet users. Many studies have shown that when users are ushered off the conventional search result pages through blue links, their needs are often partially met at best in a “hit-or-miss” fashion. To tackle this challenge, we have designed Bing, Microsoft’s decision engine, to not just navigate users to a landing page through a blue link but to continue engaging with users to clarify intent and facilitate task completion. Underlying this new paradigm is the Bing Dialog Model that consists of three building blocks: an indexing system that comprehensively collects information from the web and systematically harvests knowledge, an intent model that statistically infers user intent and predicts next action, and an interaction model that elicits user intent through mathematically optimized presentations of web information and domain knowledge that matches user needs. In this talk, I’ll describe Bing Dialog Model in details and demonstrate it in action through some innovative features since the launch of [url] |
| 关 键 词: | 互联网搜索; 意图模型 |
| 课程来源: | 视频讲座网 |
| 数据采集: | 2021-01-06：zyk |
| 最后编审: | 2021-01-08：yumf |
| 阅读次数: | 66 |