Naïve but effective NIL clustering baselines - CMCRC at TAC 2011

Will Radford, Joel Nothman, James R. Curran, Ben Hachey, Matthew Honnibal
2011 Text Analysis Conference  
This paper describes the CMCRC systems entered in the TAC 2011 entity linking challenge. We used our best-performing system from TAC 2010 to link queries, then clustered NIL links. We focused on naïve baselines that group by attributes of the top entity candidate. All three systems performed strongly at 75.4% B 3 F1, above the 71.6% median score.
dblp:conf/tac/RadfordNCHH11 fatcat:pzwasy5qjnaq5kwtk2x66bhmea