Inferring Strategies for Sentence Ordering in Multidocument News Summarization

Abstract

The problem of organizing information for multidocument summarization so that the generated summary is coherent has received relatively little attention. While sentence ordering for single document summarization can be determined from the ordering of sentences in the input article, this is not the case for multidocument summarization where summary sentences may be drawn from different input articles. In this paper, we propose a methodology for studying the properties of ordering information in the news genre and describe experiments done on a corpus of multiple acceptable orderings we developed for the task. Based on these experiments, we implemented a strategy for ordering information that combines constraints from chronological order of events and topical relatedness. Evaluation of our augmented algorithm shows a significant improvement of the ordering over two baseline strategies.

Cited by in corpus (12)

• Generating Natural Language Descriptions from OWL Ontologies: the NaturalOWL System
• A Sentence Compression Based Framework to Query-Focused Multi-Document Summarization
• Multi-document Biography Summarization
• End-to-End Neural Sentence Ordering Using Pointer Network
• Neural Sentence Ordering
• Automatic text summarization: What has been done and what has to be done
• Learning to Order Facts for Discourse Planning in Natural Language Generation
• MUDOS-NG: Multi-document Summaries Using N-gram Graphs (Tech Report)
• Graph-based Neural Sentence Ordering
• Dependencies: Formalising Semantic Catenae for Information Retrieval
• Political protest Italian-style: The dissonance between the blogosphere and mainstream media in the promotion and coverage of Beppe Grillo's V-day
• Specificity-Based Sentence Ordering for Multi-Document Extractive Risk Summarization