Toward Activity Discovery in the Personal Web
Toward Activity Discovery in the Personal Web
复制标题
DOI：
10.1145/3336191.3371828
复制
发表时间：
2020-01
期刊：
影响因子：
--
通讯作者：
Tara Safavi;Adam Fourney;Robert B Sim;Marcin Juraszek;Shane Williams;Ned Friend;Danai Koutra;Paul N. Bennett
中科院分区：
文献类型：
--
作者：
Tara Safavi;Adam Fourney;Robert B Sim;Marcin Juraszek;Shane Williams;Ned Friend;Danai Koutra;Paul N. Bennett
个人的个人信息收集（他们的电子邮件，文件，约会，网络搜索，联系人等）提供了丰富的见解，他们的日常生活的组织和结构。在本文中，我们解决了学习个人信息项的表示来捕获个人正在进行的活动（如项目和任务）的任务：这种表示可以用于以活动为中心的应用程序，如个人助理，电子邮件客户端和生产力工具，以帮助人们更好地管理他们的数据和时间。我们提出了一种基于图的方法，利用个人信息收集的固有互连结构，并获得高效，准确的技术，以增量更新表示新的数据到达。我们展示了我们的基于图形的表示对竞争力的基线在一个新的内在评级任务和外在的推荐任务的优势。
Individuals' personal information collections (their emails, files, appointments, web searches, contacts, etc) offer a wealth of insights into the organization and structure of their everyday lives. In this paper we address the task of learning representations of personal information items to capture individuals' ongoing activities, such as projects and tasks: Such representations can be used in activity-centric applications like personal assistants, email clients, and productivity tools to help people better manage their data and time. We propose a graph-based approach that leverages the inherent interconnected structure of personal information collections, and derive efficient, exact techniques to incrementally update representations as new data arrive. We demonstrate the strengths of our graph-based representations against competitive baselines in a novel intrinsic rating task and an extrinsic recommendation task.