Deep Joint Entity Disambiguation with Local Neural Attention

Code

• github.com/dalab/deep-ed
  OfficialIn papertorch★ 0
• github.com/klimzaporojets/DWIE
  pytorch★ 52
• github.com/yifding/deep_ed_PyTorch
  pytorch★ 0

Abstract

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.

Tasks

Benchmark Results

Reproductions