Query-oriented text summarization based on hypergraph transversals. Issue 4 (July 2019)

• Record Type: Journal Article
• Authors: Van Lierde, H.; Chow, Tommy W.S.
• Is Part Of: Information processing & management. Volume 56:Issue 4(2019:Jul.)
• Page Start: 1317
• Page End: 1338
• Publication Date: 2019-07
• Subjects: Query-oriented text summarization -- Hypergraph theory -- Hypergraph transversal -- Sentence clustering -- Submodular set functions; Information storage and retrieval systems -- Periodicals; Information science -- Periodicals; Systèmes d'information -- Périodiques; Sciences de l'information -- Périodiques; Information science; Information storage and retrieval systems; Periodicals; 658.4038
• DOI: 10.1016/j.ipm.2019.03.003
• Languages: English
• ISSNs: 0306-4573

Abstract

Highlights: A theoretical connection is made between sentence retrieval and the extraction of a transversal in a hypergraph. A new computationally efficient topic model is proposed, based on the semantic clustering of terms. In our hypergraph model, each hyperedge represents a topic of the corpus, and each sentence is tagged with multiple topics. The proposed algorithms are computationally cheaper than existing hypergraph-based summarizers. On real-world datasets, our model outperforms existing graph-based summarization systems by 6% of ROUGE-SU4 F-measure. Abstract: The rise in the amount of textual resources available on the Internet has created the need for tools of automatic document summarization. The main challenges of query-oriented extractive summarization are (1) to identify the topics of the documents and (2) to recover query-relevant sentences of the documents that together cover these topics. Existing graph- or hypergraph-based summarizers use graph-based ranking algorithms to produce individual scores of relevance for the sentences. Hence, these systems fail to measure the topics jointly covered by the sentences forming the summary, which tends to produce redundant summaries. To address the issue of selecting non-redundant sentences jointly covering the main query-relevant topics of a corpus, we propose a new method using the powerful theory of hypergraph transversals. First, we introduce a new topic model based on the semantic clustering of terms in order to discover the topics present in a corpus. Second, these topics are modeled as the hyperedges of a hypergraph in which the nodes are the sentences. A summary is then produced by generating a transversal of nodes in the hypergraph. Algorithms based on the theory of submodular functions are proposed to generate the transversals and to build the summaries. The proposed summarizer outperforms existing graph- or hypergraph-based summarizers by at least 6% of ROUGE-SU4 F-measure on DUC 2007 dataset. It is moreover cheaper than existing hypergraph-based summarizers in terms of computational time complexity.