Summarization of multiple documents with rhetorical annotation

Sohei Aya; Yutaka Matsuo; Naoaki Okazaki; Kôiti Hasida; Mitsuru Ishizuka

doi:10.1527/tjsai.20.149

Summarization of multiple documents with rhetorical annotation

Sohei Aya, Yutaka Matsuo, Naoaki Okazaki, Kôiti Hasida, Mitsuru Ishizuka

INF - System Information Sciences

Research output: Contribution to journal › Article › peer-review

Abstract

In this paper, we propose a new algorithm of summarization which targets a new kind of structured contents. The structured content, which is to be created by semantic authoring, consists of sentenses and rhetorical relation among sentences: It is represented by a graph, where a node is a sentence and an edge is a rhetorical relation. We simulate creating this content graph by using news paper articles that are annotated rhetorical relations by a GDA tagset. Our summarization method basically uses spreading activation over the content graph, followed by particular postprocesses to increase readability of the resultant summary. Experimental evaluation shows our method is at least equal to or better than Lead method for summarizing news paper articles.

Original language	English
Pages (from-to)	149-158
Number of pages	10
Journal	Transactions of the Japanese Society for Artificial Intelligence
Volume	20
Issue number	3
DOIs	https://doi.org/10.1527/tjsai.20.149
Publication status	Published - 2005

Keywords

Automatic summarization
Rhetorical structure theory
Semantic authoring
Spreading activation

ASJC Scopus subject areas

Software
Artificial Intelligence

Access to Document

10.1527/tjsai.20.149

Cite this

@article{b5c91c30cb51497fbbc7b0589321419b,

title = "Summarization of multiple documents with rhetorical annotation",

abstract = "In this paper, we propose a new algorithm of summarization which targets a new kind of structured contents. The structured content, which is to be created by semantic authoring, consists of sentenses and rhetorical relation among sentences: It is represented by a graph, where a node is a sentence and an edge is a rhetorical relation. We simulate creating this content graph by using news paper articles that are annotated rhetorical relations by a GDA tagset. Our summarization method basically uses spreading activation over the content graph, followed by particular postprocesses to increase readability of the resultant summary. Experimental evaluation shows our method is at least equal to or better than Lead method for summarizing news paper articles.",

keywords = "Automatic summarization, Rhetorical structure theory, Semantic authoring, Spreading activation",

author = "Sohei Aya and Yutaka Matsuo and Naoaki Okazaki and K{\^o}iti Hasida and Mitsuru Ishizuka",

year = "2005",

doi = "10.1527/tjsai.20.149",

language = "English",

volume = "20",

pages = "149--158",

journal = "Transactions of the Japanese Society for Artificial Intelligence",

issn = "1346-0714",

publisher = "Japanese Society for Artificial Intelligence",

number = "3",

}

TY - JOUR

T1 - Summarization of multiple documents with rhetorical annotation

AU - Aya, Sohei

AU - Matsuo, Yutaka

AU - Okazaki, Naoaki

AU - Hasida, Kôiti

AU - Ishizuka, Mitsuru

PY - 2005

Y1 - 2005

N2 - In this paper, we propose a new algorithm of summarization which targets a new kind of structured contents. The structured content, which is to be created by semantic authoring, consists of sentenses and rhetorical relation among sentences: It is represented by a graph, where a node is a sentence and an edge is a rhetorical relation. We simulate creating this content graph by using news paper articles that are annotated rhetorical relations by a GDA tagset. Our summarization method basically uses spreading activation over the content graph, followed by particular postprocesses to increase readability of the resultant summary. Experimental evaluation shows our method is at least equal to or better than Lead method for summarizing news paper articles.

AB - In this paper, we propose a new algorithm of summarization which targets a new kind of structured contents. The structured content, which is to be created by semantic authoring, consists of sentenses and rhetorical relation among sentences: It is represented by a graph, where a node is a sentence and an edge is a rhetorical relation. We simulate creating this content graph by using news paper articles that are annotated rhetorical relations by a GDA tagset. Our summarization method basically uses spreading activation over the content graph, followed by particular postprocesses to increase readability of the resultant summary. Experimental evaluation shows our method is at least equal to or better than Lead method for summarizing news paper articles.

KW - Automatic summarization

KW - Rhetorical structure theory

KW - Semantic authoring

KW - Spreading activation

UR - http://www.scopus.com/inward/record.url?scp=18544385148&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=18544385148&partnerID=8YFLogxK

U2 - 10.1527/tjsai.20.149

DO - 10.1527/tjsai.20.149

M3 - Article

AN - SCOPUS:18544385148

VL - 20

SP - 149

EP - 158

JO - Transactions of the Japanese Society for Artificial Intelligence

JF - Transactions of the Japanese Society for Artificial Intelligence

SN - 1346-0714

IS - 3

ER -

Summarization of multiple documents with rhetorical annotation

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this