A Trio Neural Model for Dynamic Entity Relatedness Ranking
T. Nguyen, T. Tran, and W. Nejdl. (2018)cite arxiv:1808.08316Comment: In Proceedings of CoNLL 2018.
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.
Description
A Trio Neural Model for Dynamic Entity Relatedness Ranking
%0 Generic
%1 nguyen2018neural
%A Nguyen, Tu Ngoc
%A Tran, Tuan
%A Nejdl, Wolfgang
%D 2018
%K deep_learning embeddings relatedness
%T A Trio Neural Model for Dynamic Entity Relatedness Ranking
%U http://arxiv.org/abs/1808.08316
%X 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.
@misc{nguyen2018neural,
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.},
added-at = {2018-12-12T10:17:58.000+0100},
author = {Nguyen, Tu Ngoc and Tran, Tuan and Nejdl, Wolfgang},
biburl = {https://www.bibsonomy.org/bibtex/2d3a8f7d0a3c0dea649ec2eb5be204103/dallmann},
description = {A Trio Neural Model for Dynamic Entity Relatedness Ranking},
interhash = {1ac6d5b8a7cc0b5ab7e8e575095917cd},
intrahash = {d3a8f7d0a3c0dea649ec2eb5be204103},
keywords = {deep_learning embeddings relatedness},
note = {cite arxiv:1808.08316Comment: In Proceedings of CoNLL 2018},
timestamp = {2018-12-12T10:17:58.000+0100},
title = {A Trio Neural Model for Dynamic Entity Relatedness Ranking},
url = {http://arxiv.org/abs/1808.08316},
year = 2018
}