Sentence Extraction by Spreading Activation through Sentence Similarity

Naoaki Okazaki, Yutaka Matsuo, Naohiro Matsumura, Mitsuru Ishizuka

Research output: Contribution to journalReview articlepeer-review

17 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

Keywords

  • Extraction
  • Sentence similarity
  • Spreading activation
  • Summarization

ASJC Scopus subject areas

  • Software
  • Hardware and Architecture
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering
  • Artificial Intelligence

Fingerprint Dive into the research topics of 'Sentence Extraction by Spreading Activation through Sentence Similarity'. Together they form a unique fingerprint.

Cite this