Deep Joint Entity Disambiguation with Local Neural Attention

EMNLP 2017  ·  Octavian-Eugen Ganea, Thomas 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. Our approach thereby combines benefits of deep learning with more traditional approaches such as graphical models and probabilistic mention-entity maps. Extensive experiments show that we are able to obtain competitive or state-of-the-art accuracy at moderate computational costs.

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 # 6
Entity Disambiguation AIDA-CoNLL Global In-KB Accuracy 92.22 # 14
Entity Disambiguation AQUAINT Global Micro-F1 88.5 # 5
Entity Disambiguation MSNBC Global Micro-F1 93.7 # 5
Entity Disambiguation WNED-CWEB Global Micro-F1 77.9 # 4
Entity Disambiguation WNED-WIKI Glonal Micro-F1 77.5 # 6

Methods


No methods listed for this paper. Add relevant methods here