Exploiting semantic extraction for spacial-temporal indexing in GEONODE

Marc Vilain, Rob Hyland, Rod Holland
2000 Open research Areas in Information Retrieval  
T his paper presents an approach to information access based on spatiotemporal indexing. We describe GeoNODE, a "news on demand" system that visualizes news stories and other articles in terms o f chronological tim e lines, geographical m aps, and spatiotem poral anim ations. This spatiotemporal indexing is critically inform ed by our inform ation extraction system , A lem bic. This paper thus covers several dim ensions o f the technological partnership betw een G eoN O D E and A lem bic. We
more » ... rt w ith the end product, the display of spatiotemporaliy indexed documents, and w ork our way back through the various aspects o f information extraction that underlie the indexing. We focus especially on those extraction tasks that operate at a common semantic level across diverse document sources and diverse languages. V ( M onterey Locatio j CNN Location Su GeoEvents P 1 -2 O 3 -a 0 7 -21 © 2 2 -4 5 0 40 -1 2 4
dblp:conf/riao/VilainHH00 fatcat:qaudieio2zcuxmxeid75ne6izi