Incremental Entity Summarization With Formal Concept Analysis

Abstract

Knowledge graph describes entities by numerous RDF data (subject-predicate-object triples), which has been widely applied in various fields, such as artificial intelligence, Semantic Web, entity summarization. With time elapses, the continuously increasing RDF descriptions of entity lead to information overload and further cause people confused. With this backdrop, automatic entity summarization has received much attention in recent years, aiming to select the most concise and most typical facts that depict an entity in brief from lengthy RDF data. As new descriptions of entity are continually coming, creating a compact summary of entity quickly from a lengthy knowledge graph is challenging. To address this problem, this paper firstly formulates the problem and proposes a novel approach of Incremental Entity Summarization by leveraging Formal Concept Analysis (FCA), called IES-FCA. Additionally, we not only prove the rationality of our suggested method mathematically, but also carry out extensive experiments using two real-world datasets. The experimental results demonstrate that the proposed method IES-FCA can save about 8.7% of time consumption for all entities than the non-incremental entity summarization approach KAFCA at best. As for the effectiveness, IES-FCA outperforms the stateof-the-art algorithms in terms of F 1 − measure, M AP , and N DCG.

Discovery of link keys in resource description framework datasets based on pattern structures

“…In parallel, more experiments should be performed to support and demonstrate these theoretical aspects. Finally, another direction is to study the relations existing with link discovery in Knowledge Graphs and more generally in the web of data [32,33], especially link prediction [34] and entity summarization [35].…”