scispace - formally typeset
Search or ask a question

Showing papers by "José Luis Ambite published in 2008"


Journal ArticleDOI
TL;DR: The goal of the Electric Elves project was to develop software agent technology to support human organizations, and a variety of applications of the Elves were developed, including scheduling visitors, man- aging a research group, and monitoring travel.
Abstract: The goal of the Electric Elves project was to develop software agent technology to support human organizations. We developed a variety of applications of the Elves, including scheduling visitors, man- aging a research group (the Office Elves), and monitoring travel (the Travel Elves). The Travel Elves were eventually deployed at DARPA, where things did not go exact- ly as planned. In this article, we describe some of the things that went wrong and then present some of the lessons learned and new research that arose from our experience in building the Travel Elves.

9 citations


Proceedings ArticleDOI
15 Dec 2008
TL;DR: An end-to-end validation of the Deimos system in two information domains is provided to show that it can successfully discover and model new data sources in those domains.
Abstract: We describe Deimos, a system that automatically discovers and models new sources of information.The system exploits four core technologies developed by our group that makes an end-to-end solution to this problem possible. First, given an example source, Deimos finds other similar sources online. Second, it invokes and extracts data from these sources. Third, given the syntactic structure of a source, Deimos maps its inputs and outputs to semantic types. Finally, it infers the source's semantic definition, i.e., the function that maps the inputs to the outputs. Deimos is able to successfully automate these steps by exploiting a combination of background knowledge and data semantics. We describe the challenges in integrating separate components into a unified approach to discovering, extracting and modeling new online sources. We provide an end-to-end validation of the system in two information domains to show that it can successfully discover and model new data sources in those domains.

7 citations