English

A Trio Neural Model for Dynamic Entity Relatedness Ranking

Information Retrieval 2025-12-01 v5 Computation and Language Machine Learning Machine Learning

Abstract

Measuring entity relatedness is a fundamental task for many natural language processing and information retrieval applications. Prior work often studies entity relatedness in static settings and an unsupervised manner. However, entities in real-world are often involved in many different relationships, consequently entity-relations are very dynamic over time. In this work, we propose a neural networkbased approach for dynamic entity relatedness, leveraging the collective attention as supervision. Our model is capable of learning rich and different entity representations in a joint framework. Through extensive experiments on large-scale datasets, we demonstrate that our method achieves better results than competitive baselines.

Keywords

Cite

@article{arxiv.1808.08316,
  title  = {A Trio Neural Model for Dynamic Entity Relatedness Ranking},
  author = {Tu Nguyen and Tuan Tran and Wolfgang Nejdl},
  journal= {arXiv preprint arXiv:1808.08316},
  year   = {2025}
}

Comments

In Proceedings of CoNLL 2018

R2 v1 2026-06-23T03:43:24.649Z