Coherent arrangement of sentences extracted from multiple newspaper articles

被引:0
|
作者
Okazaki, N
Matsuo, Y
Ishizuka, M
机构
[1] Univ Tokyo, Grad Sch Informat Sci & Technol, Bunkyo Ku, Tokyo 1138656, Japan
[2] AIST, Cyber Assist Res Ctr, Koto Ku, Tokyo 1350064, Japan
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
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.
引用
收藏
页码:882 / 891
页数:10
相关论文
共 50 条
  • [31] Synthesis and Application of Methylcellulose Extracted from Waste Newspaper in CPV-ARI Portland Cement Mortars
    Oliveira, Geandre de Carvalho
    Rodrigues Filho, Guimes
    Vieira, Julia Graciele
    Nascimento De Assuncao, Rosana M.
    Meireles, Carla da Silva
    Cerqueira, Daniel Alves
    de Oliveira, Reginaldo Joao
    Silva, Wanderly Geraldo
    de Castro Motta, Leila Aparecida
    JOURNAL OF APPLIED POLYMER SCIENCE, 2010, 118 (03) : 1380 - 1385
  • [32] Networks of Names: Visual Exploration and Semi-Automatic Tagging of Social Networks from Newspaper Articles
    Kochtchi, A.
    von Landesberger, T.
    Biemann, C.
    COMPUTER GRAPHICS FORUM, 2014, 33 (03) : 211 - 220
  • [33] Representations of the subject 'woman' and the politics of abortion: an analysis of South African newspaper articles from 1978 to 2005
    Macleod, Catriona Ida
    Feltham-King, Tracey
    CULTURE HEALTH & SEXUALITY, 2012, 14 (07) : 737 - 752
  • [34] Learning from masked analogies between sentences at multiple levels of formality
    Wang, Liyan
    Lepage, Yves
    ANNALS OF MATHEMATICS AND ARTIFICIAL INTELLIGENCE, 2023,
  • [35] Polarity Assignment to Causal Information Extracted from Financial Articles Concerning Business Performance of Companies
    Sakai, Hiroyuki
    Masuyama, Shigeru
    RESEARCH AND DEVELOPMENT IN INTELLIGENT SYSTEMS XXV, 2009, : 307 - 320
  • [36] Chemical compositions extracted from Wikstroemia indica and their multiple activities
    Lu, Chuan-Li
    Zhu, Liang
    Piao, Jin-Hua
    Jiang, Jian-Guo
    PHARMACEUTICAL BIOLOGY, 2012, 50 (02) : 225 - 231
  • [37] Evaluation of Topic Identification Methods for Arabic Texts and their Combination by using a Corpus Extracted from the Omani Newspaper Alwatan
    Abbas, M.
    Smaili, K.
    Berkani, D.
    ARAB GULF JOURNAL OF SCIENTIFIC RESEARCH, 2011, 29 (3-4): : 183 - 191
  • [38] Making sense of data using automated content analysis: an illustration using archival data from newspaper articles
    Mathew, Sunil George
    JOURNAL OF MARKETING ANALYTICS, 2024,
  • [39] What's the message? A content analysis of newspaper articles about assisted reproductive technology from 2005 to 2011
    King, L.
    Tulandi, T.
    Whitley, R.
    Constantinescu, T.
    Ells, C.
    Zelkowitz, P.
    HUMAN FERTILITY, 2014, 17 (02) : 124 - 132
  • [40] Coherent Reconstruction of Multiple Humans from a Single Image
    Jiang, Wen
    Kolotouros, Nikos
    Pavlakos, Georgios
    Zhou, Xiaowei
    Daniilidis, Kostas
    2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2020, : 5578 - 5587