Dependency-based sentence alignment for multiple document summarization

Tsutomu Hirao; Jun Suzuki; Hideki Isozaki; Eisaku Maeda

Dependency-based sentence alignment for multiple document summarization

Tsutomu Hirao, Jun Suzuki, Hideki Isozaki, Eisaku Maeda

Research output: Contribution to conference › Paper › peer-review

Abstract

In this paper, we describe a method of automatic sentence alignment for building extracts from abstracts in automatic summarization research. Our method is based on two steps. First, we introduce the “dependency tree path” (DTP). Next, we calculate the similarity between DTPs based on the ESK (Extended String Subsequence Kernel), which considers sequential patterns. By using these procedures, we can derive one-to-many or many-to-one correspondences among sentences. Experiments using different similarity measures show that DTP consistently improves the alignment accuracy and that ESK gives the best performance.

Original language	English
Publication status	Published - 2004
Externally published	Yes
Event	20th International Conference on Computational Linguistics, COLING 2004 - Geneva, Switzerland Duration: 2004 Aug 23 → 2004 Aug 27

Conference

Conference	20th International Conference on Computational Linguistics, COLING 2004
Country/Territory	Switzerland
City	Geneva
Period	04/8/23 → 04/8/27

ASJC Scopus subject areas

Computational Theory and Mathematics
Language and Linguistics
Linguistics and Language

Cite this

@conference{3ef64d90a2354ca49ef62783c615a921,

title = "Dependency-based sentence alignment for multiple document summarization",

abstract = "In this paper, we describe a method of automatic sentence alignment for building extracts from abstracts in automatic summarization research. Our method is based on two steps. First, we introduce the “dependency tree path” (DTP). Next, we calculate the similarity between DTPs based on the ESK (Extended String Subsequence Kernel), which considers sequential patterns. By using these procedures, we can derive one-to-many or many-to-one correspondences among sentences. Experiments using different similarity measures show that DTP consistently improves the alignment accuracy and that ESK gives the best performance.",

author = "Tsutomu Hirao and Jun Suzuki and Hideki Isozaki and Eisaku Maeda",

note = "Publisher Copyright: {\textcopyright} 2004 COLING 2004 - Proceedings of the 20th International Conference on Computational Linguistics. All rights reserved.; 20th International Conference on Computational Linguistics, COLING 2004 ; Conference date: 23-08-2004 Through 27-08-2004",

year = "2004",

language = "English",

}

TY - CONF

T1 - Dependency-based sentence alignment for multiple document summarization

AU - Hirao, Tsutomu

AU - Suzuki, Jun

AU - Isozaki, Hideki

AU - Maeda, Eisaku

PY - 2004

Y1 - 2004

N2 - In this paper, we describe a method of automatic sentence alignment for building extracts from abstracts in automatic summarization research. Our method is based on two steps. First, we introduce the “dependency tree path” (DTP). Next, we calculate the similarity between DTPs based on the ESK (Extended String Subsequence Kernel), which considers sequential patterns. By using these procedures, we can derive one-to-many or many-to-one correspondences among sentences. Experiments using different similarity measures show that DTP consistently improves the alignment accuracy and that ESK gives the best performance.

AB - In this paper, we describe a method of automatic sentence alignment for building extracts from abstracts in automatic summarization research. Our method is based on two steps. First, we introduce the “dependency tree path” (DTP). Next, we calculate the similarity between DTPs based on the ESK (Extended String Subsequence Kernel), which considers sequential patterns. By using these procedures, we can derive one-to-many or many-to-one correspondences among sentences. Experiments using different similarity measures show that DTP consistently improves the alignment accuracy and that ESK gives the best performance.

UR - http://www.scopus.com/inward/record.url?scp=52949107089&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=52949107089&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:52949107089

T2 - 20th International Conference on Computational Linguistics, COLING 2004

Y2 - 23 August 2004 through 27 August 2004

ER -

Dependency-based sentence alignment for multiple document summarization

Abstract

Conference

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this