Sentence Extraction by Spreading Activation through Sentence Similarity

Naoaki Okazaki, Yutaka Matsuo, Naohiro Matsumura, Mitsuru Ishizuka

Research output: Contribution to journalArticle

14 Citations (Scopus)

Abstract

Although there has been a great deal of research on automatic summarization, most methods rely on statistical methods, disregarding relationships between extracted textual segments. We propose a novel method to extract a set of comprehensible sentences which centers on several key points to ensure sentence connectivity. It features a similarity network from documents with a lexical dictionary, and spreading activation to rank sentences. We show evaluation results of a multi-document summarization system based on the method participating in a competition of summarization, TSC (Text Summarization Challenge) task, organized by the third NTCIR project.

Original languageEnglish
Pages (from-to)1686-1694
Number of pages9
JournalIEICE Transactions on Information and Systems
VolumeE86-D
Issue number9
Publication statusPublished - 2003 Sep
Externally publishedYes

Fingerprint

Glossaries
Statistical methods
Chemical activation

Keywords

  • Extraction
  • Sentence similarity
  • Spreading activation
  • Summarization

ASJC Scopus subject areas

  • Information Systems
  • Computer Graphics and Computer-Aided Design
  • Software

Cite this

Okazaki, N., Matsuo, Y., Matsumura, N., & Ishizuka, M. (2003). Sentence Extraction by Spreading Activation through Sentence Similarity. IEICE Transactions on Information and Systems, E86-D(9), 1686-1694.

Sentence Extraction by Spreading Activation through Sentence Similarity. / Okazaki, Naoaki; Matsuo, Yutaka; Matsumura, Naohiro; Ishizuka, Mitsuru.

In: IEICE Transactions on Information and Systems, Vol. E86-D, No. 9, 09.2003, p. 1686-1694.

Research output: Contribution to journalArticle

Okazaki, N, Matsuo, Y, Matsumura, N & Ishizuka, M 2003, 'Sentence Extraction by Spreading Activation through Sentence Similarity', IEICE Transactions on Information and Systems, vol. E86-D, no. 9, pp. 1686-1694.
Okazaki N, Matsuo Y, Matsumura N, Ishizuka M. Sentence Extraction by Spreading Activation through Sentence Similarity. IEICE Transactions on Information and Systems. 2003 Sep;E86-D(9):1686-1694.
Okazaki, Naoaki ; Matsuo, Yutaka ; Matsumura, Naohiro ; Ishizuka, Mitsuru. / Sentence Extraction by Spreading Activation through Sentence Similarity. In: IEICE Transactions on Information and Systems. 2003 ; Vol. E86-D, No. 9. pp. 1686-1694.
@article{23a70e5360a44ee9a6b6b0ed62c1dd94,
title = "Sentence Extraction by Spreading Activation through Sentence Similarity",
abstract = "Although there has been a great deal of research on automatic summarization, most methods rely on statistical methods, disregarding relationships between extracted textual segments. We propose a novel method to extract a set of comprehensible sentences which centers on several key points to ensure sentence connectivity. It features a similarity network from documents with a lexical dictionary, and spreading activation to rank sentences. We show evaluation results of a multi-document summarization system based on the method participating in a competition of summarization, TSC (Text Summarization Challenge) task, organized by the third NTCIR project.",
keywords = "Extraction, Sentence similarity, Spreading activation, Summarization",
author = "Naoaki Okazaki and Yutaka Matsuo and Naohiro Matsumura and Mitsuru Ishizuka",
year = "2003",
month = "9",
language = "English",
volume = "E86-D",
pages = "1686--1694",
journal = "IEICE Transactions on Information and Systems",
issn = "0916-8532",
publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
number = "9",

}

TY - JOUR

T1 - Sentence Extraction by Spreading Activation through Sentence Similarity

AU - Okazaki, Naoaki

AU - Matsuo, Yutaka

AU - Matsumura, Naohiro

AU - Ishizuka, Mitsuru

PY - 2003/9

Y1 - 2003/9

N2 - Although there has been a great deal of research on automatic summarization, most methods rely on statistical methods, disregarding relationships between extracted textual segments. We propose a novel method to extract a set of comprehensible sentences which centers on several key points to ensure sentence connectivity. It features a similarity network from documents with a lexical dictionary, and spreading activation to rank sentences. We show evaluation results of a multi-document summarization system based on the method participating in a competition of summarization, TSC (Text Summarization Challenge) task, organized by the third NTCIR project.

AB - Although there has been a great deal of research on automatic summarization, most methods rely on statistical methods, disregarding relationships between extracted textual segments. We propose a novel method to extract a set of comprehensible sentences which centers on several key points to ensure sentence connectivity. It features a similarity network from documents with a lexical dictionary, and spreading activation to rank sentences. We show evaluation results of a multi-document summarization system based on the method participating in a competition of summarization, TSC (Text Summarization Challenge) task, organized by the third NTCIR project.

KW - Extraction

KW - Sentence similarity

KW - Spreading activation

KW - Summarization

UR - http://www.scopus.com/inward/record.url?scp=1642391650&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=1642391650&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:1642391650

VL - E86-D

SP - 1686

EP - 1694

JO - IEICE Transactions on Information and Systems

JF - IEICE Transactions on Information and Systems

SN - 0916-8532

IS - 9

ER -