Deep Joint Entity Disambiguation with Local Neural Attention
This work addresses entity disambiguation for natural language processing applications, presenting an incremental improvement by combining deep learning with traditional methods.
The paper tackles the problem of joint document-level entity disambiguation by proposing a deep learning model that integrates entity embeddings, neural attention over local contexts, and differentiable joint inference, achieving competitive or state-of-the-art accuracy with moderate computational costs.
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.