DeepLENS: Deep Learning for Entity Summarization

TL;DR

DeepLENS introduces a deep learning approach leveraging textual semantics to improve entity summarization in knowledge graphs, outperforming existing methods on benchmark datasets.

Contribution

It presents a novel deep learning model that encodes triples using textual semantics and scores their interdependence, enhancing entity summarization.

Findings

DeepLENS significantly outperforms existing methods on benchmark datasets.

The model effectively exploits textual semantics for triple encoding.

Interdependence scoring improves the quality of entity summaries.

Abstract

Entity summarization has been a prominent task over knowledge graphs. While existing methods are mainly unsupervised, we present DeepLENS, a simple yet effective deep learning model where we exploit textual semantics for encoding triples and we score each candidate triple based on its interdependence on other triples. DeepLENS significantly outperformed existing methods on a public benchmark.