Ontology-based Extractive Text Summarization: The Contribution of Instances

In this paper, we present a text summarization approach focusing on multi-document, extractive and query-focused summarization that relies on an ontology-based semantic similarity measure, that specifically explores ontology instances. We employ the DBpedia Ontology and a theoretical definition of similarity to determine query-sentence and sentence-sentence similarity. Furthermore, we define an instance-linking strategy that builds the most accurate sentence representation possible while achieving a better coverage of sentences that can be represented by ontology instances. Using primarily this instances linking strategy, the semantic similarity measure and the Maximal Marginal Relevance Algorithm (MMR), we propose a summarization model that is capable of avoiding redundancy from a more fine-grained representation of sentences, due to their representation as ontology instances. We demonstrate that our summarizer is capable of achieving compelling results when compared with relevant DUC systems and recently published related studies using ROUGE metrics. Moreover, our experiments lead us to a better understanding of how ontology instances can be used to represent sentences and what is the role of said instances in this process.