Coherent arrangement of sentences extracted from multiple newspaper articles

Naoaki Okazaki, Yutaka Matsuo, Mitsuru Ishizuka

Research output: Contribution to journalConference article

5 Citations (Scopus)

Abstract

Multi-document summarization is a challenge to information overload problem to provide a condensed text for a number of documents. Most multi-document summarization systems make use of extraction techniques (e.g., important sentence extraction) and compile a summary from the selected information. However, sentences gathered from multiple sources are not organized as a comprehensible text. Therefore, it is important to consider sentence ordering of extracted sentences in order to reconstruct discourse structure in a summary. We propose a novel method to plan a coherent arrangement of sentences extracted from multiple newspaper articles. Results of our experiment show that sentence reordering has a discernible effect on summary readability. The results also shows significant improvement on sentence arrangement compared to former methods.

Original languageEnglish
Pages (from-to)882-891
Number of pages10
JournalLecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science)
Volume3157
DOIs
Publication statusPublished - 2004 Jan 1
Event8th Pacific Rim International Conference on Artificial Intelligence, PRICAI 2004: Trends in Artificial Intelligence - Auckland, New Zealand
Duration: 2004 Aug 92004 Aug 13

ASJC Scopus subject areas

  • Theoretical Computer Science
  • Computer Science(all)

Fingerprint Dive into the research topics of 'Coherent arrangement of sentences extracted from multiple newspaper articles'. Together they form a unique fingerprint.

  • Cite this