List your company
ResearchFormerly WizWand

Entity Linking on WIKI (test)

84.5Micro F1WNED
59.300865.842972.38578.9271Sep 4, 2019Sep 24, 2019Oct 15, 2019Nov 5, 2019Nov 25, 2019Dec 16, 2019Jan 6, 2020
Updated 8mo ago

Evaluation results

MethodLinks
WNED2019.0984.5
Guo and Barbosa (2016)2020.0184.5
Oracle type (FIGER)Type source=FIGER, Mode=Oracle2020.0184.4
Oracle type (Ultra-fine)Type source=Ultra-fine, Mode=Oracle2020.0184
Milne and Witten (2008)2020.0181.7
BERT-Entity-Sim (local & global)2020.0180.1
ETHZ-Attn + DCA-RLBackbone=ETHZ-Attn, Learning protocol=Reinforcement Learning2019.0978.84
ETHZ-Attn + DCA-SLBackbone=ETHZ-Attn, Learning protocol=Supervised Learning2019.0978.16
Ment-Norm2019.0978
Le and Titov (2018)2020.0178
Deep-ED2019.0977.5
Ganea and Hofmann (2017)2020.0177.5
Predict type (ZOE)Type source=ZOE, Mode=Predicted2020.0177
Predict type (Ultra-fine)Type source=Ultra-fine, Mode=Predicted2020.0176.8
BERT+G&H's embeddings2020.0176.3
ETHZ-AttnBackbone=ETHZ-Attn2019.0974.37
Berkeley-CNN + DCA-RLBackbone=Berkeley-CNN, Learning protocol=Reinforcement Learning2019.0973.98
RI2019.0973.4
Cheng and Roth (2013)2020.0173.4
Berkeley-CNN + DCA-SLBackbone=Berkeley-CNN, Learning protocol=Supervised Learning2019.0972.55
GLOW2019.0967.2
Ratinov et al. (2011)2020.0167.2
Prior (p(e|m))2019.0964.2
prior p(e|m)2020.0164.2
AIDA2019.0963
Hoffart et al. (2011)2020.0163
Berkeley-CNNBackbone=Berkeley-CNN2019.0960.27