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

arXiv: https://arxiv.org/abs/1906.09320 · HTML: https://mlsanity.com/paper/1906.09320/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Jun 2019.

## Built on by (most cited first, 4 of 4)

- [Entity Linking Meets Deep Learning: Techniques and Solutions](https://mlsanity.com/paper/2109.12520/) (2021)
- [Community Question Answering Entity Linking via Leveraging Auxiliary Data](https://mlsanity.com/paper/2205.11917/) (2022)
- [Improving Graph-based Sentence Ordering with Iteratively Predicted Pairwise Orderings](https://mlsanity.com/paper/2110.06446/) (2021)
- [Learning Entity Linking Features for Emerging Entities](https://mlsanity.com/paper/2208.03877/) (2022)

## Abstract (arXiv)

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 urlhttps://github.com/DeepLearnXMU/RRWEL.