Our group is involved in the European funded Webocracy project in which an e-government system called Webocrat has been designed and implemented. Our responsibility is to provide m...
Traditional Information Extraction (IE) takes a relation name and hand-tagged examples of that relation as input. Open IE is a relationindependent extraction paradigm that is tail...
In this paper, we describe our work in progress in the scope of information retrieval exploiting the spatial data extracted from web documents. We discuss problems of a search for ...
Stefan Dlugolinsky, Michal Laclavik, Ladislav Hluc...
In this paper, we describe the lessons we learned in developing AgentBuilder, a commercial system for rapidly creating agents that extract information from web sites. AgentBuilder...
In this paper, a motion-based approach for detecting high-level semantic events in video sequences is presented. Its main characteristic is its generic nature, i.e. it can be dire...