Loading...
Please wait, while we are loading the content...
Similar Documents
Watson : An Infrastructure for Providing Task-Relevant , Just-InTime Information
| Content Provider | Semantic Scholar |
|---|---|
| Author | Budzik, Jay Hammond, Kristian J. |
| Copyright Year | 2007 |
| Abstract | We describe a class of systems called Information Management Assistants (IMAs). IMAs observe users as they go about completing a task in everyday software applications, and use these observations to anticipate a user’s information needs. They then automatically fulfill these needs by querying traditional information sources, filtering the results and presenting them to the user. IMAs provide a framework for bringing implicit task context to bear on servicing explicit information requests, significantly reducing ambiguity. IMAs embody a just-in-time information infrastructure in which information is brought to users as they need it, without requiring explicit requests. In this paper, we present our work on an architecture for this class of system, and our progress implementing Watson, a prototype of such a system. Watson observes users in word processing and web browsing applications and uses a model of the user’s tasks, knowledge of term importance, and an understanding of query generation to find relevant documents and service explicit queries. We close by discussing our preliminary results. |
| File Format | PDF HTM / HTML |
| Alternate Webpage(s) | http://www.infolab.nwu.edu/~jlbudzik/watson/aaai99/workshop3.ps |
| Language | English |
| Access Restriction | Open |
| Content Type | Text |
| Resource Type | Article |
