Literature/1998/Bollacker


 * http://portal.acm.org/citation.cfm?id=280786&CFID=27098096&CFTOKEN=10118008

Abstract
Research papers available on the World Wide Web (WWW or Web) are often poorly organized, often exist in forms opaque to search engines (e.g. Postscript), and increase in quantity daily. Significant amounts of time and effort are typically needed in order to find interesting and relevant publications on the Web. We have developed a Web based information agent that assists the user in the process of performing a scientific literature search. Given a set of keywords, the agent uses Web search engines and heuristics to locate and download papers. The papers are parsed in order to extract information features such as the abstract and individually identified citations. The agents Web interface can be used to find relevant papers in the database using keyword searches, or by navigating the links between papers formed by the citations. Links to both citing and cited publications can be followed. In addition to simple browsing and keyword searches, the agent can find papers which are similar to a given paper using word information and by analyzing common citations made by the papers.

Wikimedia

 * CiteSeer
 * CiteSeerX