# Neural Collective Entity Linking Based on Recurrent Random Walk Network Learning

## TL;DR

This paper introduces a neural network model with recurrent random-walk layers that leverages external knowledge to improve collective entity linking accuracy by modeling semantic interdependence among decisions.

## Contribution

It proposes a novel end-to-end neural network architecture that incorporates external knowledge through random-walk layers and a semantic regularizer for enhanced collective entity linking.

## Key findings

- Outperforms state-of-the-art models on various datasets
- Effectively models semantic interdependence with external knowledge
- Achieves higher disambiguation accuracy

## Abstract

Benefiting from the excellent ability of neural networks on learning semantic representations, existing studies for entity linking (EL) have resorted to neural networks to exploit both the local mention-to-entity compatibility and the global interdependence between different EL decisions for target entity disambiguation. However, most neural collective EL methods depend entirely upon neural networks to automatically model the semantic dependencies between different EL decisions, which lack of the guidance from external knowledge. In this paper, we propose a novel end-to-end neural network with recurrent random-walk layers for collective EL, which introduces external knowledge to model the semantic interdependence between different EL decisions. Specifically, we first establish a model based on local context features, and then stack random-walk layers to reinforce the evidence for related EL decisions into high-probability decisions, where the semantic interdependence between candidate entities is mainly induced from an external knowledge base. Finally, a semantic regularizer that preserves the collective EL decisions consistency is incorporated into the conventional objective function, so that the external knowledge base can be fully exploited in collective EL decisions. Experimental results and in-depth analysis on various datasets show that our model achieves better performance than other state-of-the-art models. Our code and data are released at \url{https://github.com/DeepLearnXMU/RRWEL}.