Deep Joint Entity Disambiguation with Local Neural Attention

EMNLP 2017 Octavian-Eugen GaneaThomas Hofmann

We propose a novel deep learning model for joint document-level entity disambiguation, which leverages learned neural representations. Key components are entity embeddings, a neural attention mechanism over local context windows, and a differentiable joint inference stage for disambiguation... (read more)

PDF Abstract EMNLP 2017 PDF EMNLP 2017 Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Entity Disambiguation ACE2004 Global Micro-F1 88.5 # 3
Entity Disambiguation AIDA-CoNLL Global Micro-F1 92.22 # 5
Entity Disambiguation AQUAINT Global Micro-F1 88.5 # 3
Entity Disambiguation MSNBC Global Micro-F1 93.7 # 3
Entity Disambiguation WNED-CWEB Global Micro-F1 77.9 # 2
Entity Disambiguation WNED-WIKI Glonal Micro-F1 77.5 # 3

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet