A Trio Neural Model for Dynamic Entity Relatedness Ranking

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Nguyen, Tu, Tran, Tuan, Nejdl, Wolfgang
Format: Preprint
Publié: 2018
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866908677825363968
author Nguyen, Tu
Tran, Tuan
Nejdl, Wolfgang
author_facet Nguyen, Tu
Tran, Tuan
Nejdl, Wolfgang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_1808_08316
institution arXiv
publishDate 2018
record_format arxiv
spellingShingle A Trio Neural Model for Dynamic Entity Relatedness Ranking
Nguyen, Tu
Tran, Tuan
Nejdl, Wolfgang
Information Retrieval
Computation and Language
Machine Learning
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.
title A Trio Neural Model for Dynamic Entity Relatedness Ranking
topic Information Retrieval
Computation and Language
Machine Learning
url https://arxiv.org/abs/1808.08316