# Neural Collective Entity Linking

arXiv: https://arxiv.org/abs/1811.08603 · HTML: https://mlsanity.com/paper/1811.08603/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Nov 2018.

## Built on by (most cited first, 21 of 21)

- [Entity Linking Meets Deep Learning: Techniques and Solutions](https://mlsanity.com/paper/2109.12520/) (2021)
- [CHOLAN: A Modular Approach for Neural Entity Linking on Wikipedia and Wikidata](https://mlsanity.com/paper/2101.09969/) (2021)
- [Multi-Grained Multimodal Interaction Network for Entity Linking](https://mlsanity.com/paper/2307.09721/) (2023)
- [Medical Entity Disambiguation Using Graph Neural Networks](https://mlsanity.com/paper/2104.01488/) (2021)
- [Improving Candidate Retrieval with Entity Profile Generation for Wikidata Entity Linking](https://mlsanity.com/paper/2202.13404/) (2022)
- [DRIN: Dynamic Relation Interactive Network for Multimodal Entity Linking](https://mlsanity.com/paper/2310.05589/) (2023)
- [Self-Supervised Knowledge Assimilation for Expert-Layman Text Style Transfer](https://mlsanity.com/paper/2110.02950/) (2021)
- [EDIN: An End-to-end Benchmark and Pipeline for Unknown Entity Discovery and Indexing](https://mlsanity.com/paper/2205.12570/) (2022)
- [Optimal Transport Guided Correlation Assignment for Multimodal Entity Linking](https://mlsanity.com/paper/2406.01934/) (2024)
- [Personalized Entity Resolution with Dynamic Heterogeneous Knowledge Graph Representations](https://mlsanity.com/paper/2104.02667/) (2021)
- [Knowledge-Enhanced Recommendation with User-Centric Subgraph Network](https://mlsanity.com/paper/2403.14377/) (2024)
- [Learning Entity Linking Features for Emerging Entities](https://mlsanity.com/paper/2208.03877/) (2022)
- [Knowledge is Power, Understanding is Impact: Utility and Beyond Goals, Explanation Quality, and Fairness in Path Reasoning Recommendation](https://mlsanity.com/paper/2301.05944/) (2023)
- [Multi-level Matching Network for Multimodal Entity Linking](https://mlsanity.com/paper/2412.10440/) (2024)
- [An entity-guided text summarization framework with relational heterogeneous graph neural network](https://mlsanity.com/paper/2302.03205/) (2023)
- [Better Together -- An Ensemble Learner for Combining the Results of Ready-made Entity Linking Systems](https://mlsanity.com/paper/2101.05634/) (2021)
- [Graph Neural Networks for Inconsistent Cluster Detection in Incremental Entity Resolution](https://mlsanity.com/paper/2105.05957/) (2021)
- [Learning to Select the Next Reasonable Mention for Entity Linking](https://mlsanity.com/paper/2112.04104/) (2021)
- [Intent-aware Multi-source Contrastive Alignment for Tag-enhanced Recommendation](https://mlsanity.com/paper/2211.06370/) (2022)
- [Multi-level Mixture of Experts for Multimodal Entity Linking](https://mlsanity.com/paper/2507.07108/) (2025)
- [PGMEL: Policy Gradient-based Generative Adversarial Network for Multimodal Entity Linking](https://mlsanity.com/paper/2510.02726/) (2025)

## Abstract (arXiv)

Entity Linking aims to link entity mentions in texts to knowledge bases, and neural models have achieved recent success in this task. However, most existing methods rely on local contexts to resolve entities independently, which may usually fail due to the data sparsity of local information. To address this issue, we propose a novel neural model for collective entity linking, named as NCEL. NCEL applies Graph Convolutional Network to integrate both local contextual features and global coherence information for entity linking. To improve the computation efficiency, we approximately perform graph convolution on a subgraph of adjacent entity mentions instead of those in the entire text. We further introduce an attention scheme to improve the robustness of NCEL to data noise and train the model on Wikipedia hyperlinks to avoid overfitting and domain bias. In experiments, we evaluate NCEL on five publicly available datasets to verify the linking performance as well as generalization ability. We also conduct an extensive analysis of time complexity, the impact of key modules, and qualitative results, which demonstrate the effectiveness and efficiency of our proposed method.