End-to-End Neural Entity Linking

CONLL 2018 Nikolaos KolitsasOctavian-Eugen GaneaThomas Hofmann

Entity Linking (EL) is an essential task for semantic text understanding and information extraction. Popular methods separately address the Mention Detection (MD) and Entity Disambiguation (ED) stages of EL, without leveraging their mutual dependency... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Entity Linking Derczynski E2E Micro-F1 42.3 # 1
Entity Linking MSNBC E2E Micro-F1 72.4 # 1
Entity Linking N3-Reuters-128 E2E Micro-F1 54.6 # 1
Entity Linking OKE-2015 E2E Micro-F1 66.9 # 1
Entity Linking OKE-2016 E2E Micro-F1 58.4 # 1