Capturing Semantic Similarity for Entity Linking with Convolutional Neural Networks

TL;DR

This paper introduces a convolutional neural network-based model that effectively captures semantic context for entity linking, significantly improving disambiguation accuracy across multiple datasets.

Contribution

It presents a novel CNN-based approach operating at multiple granularities to model semantic similarity in entity linking, outperforming previous methods.

Findings

Achieved state-of-the-art performance on multiple datasets.

Outperformed prior systems by significant margins.

Demonstrated the effectiveness of multi-granularity CNNs in semantic modeling.

Abstract

A key challenge in entity linking is making effective use of contextual information to disambiguate mentions that might refer to different entities in different contexts. We present a model that uses convolutional neural networks to capture semantic correspondence between a mention's context and a proposed target entity. These convolutional networks operate at multiple granularities to exploit various kinds of topic information, and their rich parameterization gives them the capacity to learn which n-grams characterize different topics. We combine these networks with a sparse linear model to achieve state-of-the-art performance on multiple entity linking datasets, outperforming the prior systems of Durrett and Klein (2014) and Nguyen et al. (2014).