UCD IIRG at TAC KBP 2013
Lorna Byrne, Caroline Fenlon, John Dunnion · Theory and applications of categories · 2013
This paper describes the IIRG system entered in the TAC 2013 Knowledge Base Population Track. The overall goal of KBP is to automatically identify salient and novel entities from multiple languages, link them to corresponding Knowledge Base (KB) entries (if the linkage exists) in a target language, then discover attributes about the entities (extract temporal spans about the attributes if there exist dynamic changes), and nally expand the KB with any new attributes (Ji et al., 2011).