Topic relatedness in evaluative information extraction

Takuya Kawada; Tetsuji Nakagawa; Kentaro Inui; Sadao Kurohashi

doi:10.1145/1667780.1667804

Topic relatedness in evaluative information extraction

Takuya Kawada, Tetsuji Nakagawa, Kentaro Inui, Sadao Kurohashi

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

2 Citations (Scopus)

Abstract

The task of extracting opinions/evaluations related to a given topic from a large number of documents such as Web documents is crucial for developing an automatic evaluation finding system, which can handle a wide variety of topics as input. In this paper, we discuss the topic relatedness of extracted evaluation through analysis of a corpus we developed. We suggest here that the semantic relationship between the target of each extracted evaluation and a given topic helps in judging topic relatedness. In addition, we point out other factors that are beyond the analysis of topic-target relations for judging the topic relatedness of evaluation.

Original language	English
Title of host publication	Proceedings of the 3rd International Universal Communication Symposium, IUCS 2009
Pages	120-125
Number of pages	6
DOIs	https://doi.org/10.1145/1667780.1667804
Publication status	Published - 2009
Externally published	Yes
Event	3rd International Universal Communication Symposium, IUCS 2009 - Tokyo, Japan Duration: 2009 Dec 3 → 2009 Dec 4

Publication series

Name	ACM International Conference Proceeding Series

Other

Other	3rd International Universal Communication Symposium, IUCS 2009
Country/Territory	Japan
City	Tokyo
Period	09/12/3 → 09/12/4

ASJC Scopus subject areas

Software
Human-Computer Interaction
Computer Vision and Pattern Recognition
Computer Networks and Communications

Access to Document

10.1145/1667780.1667804

Cite this

Kawada, T, Nakagawa, T, Inui, K & Kurohashi, S 2009, Topic relatedness in evaluative information extraction. in Proceedings of the 3rd International Universal Communication Symposium, IUCS 2009. ACM International Conference Proceeding Series, pp. 120-125, 3rd International Universal Communication Symposium, IUCS 2009, Tokyo, Japan, 09/12/3. https://doi.org/10.1145/1667780.1667804

@inproceedings{c07d2ec8442345259f33385e18bc9eb2,

title = "Topic relatedness in evaluative information extraction",

abstract = "The task of extracting opinions/evaluations related to a given topic from a large number of documents such as Web documents is crucial for developing an automatic evaluation finding system, which can handle a wide variety of topics as input. In this paper, we discuss the topic relatedness of extracted evaluation through analysis of a corpus we developed. We suggest here that the semantic relationship between the target of each extracted evaluation and a given topic helps in judging topic relatedness. In addition, we point out other factors that are beyond the analysis of topic-target relations for judging the topic relatedness of evaluation.",

author = "Takuya Kawada and Tetsuji Nakagawa and Kentaro Inui and Sadao Kurohashi",

year = "2009",

doi = "10.1145/1667780.1667804",

language = "English",

isbn = "9781605586410",

series = "ACM International Conference Proceeding Series",

pages = "120--125",

booktitle = "Proceedings of the 3rd International Universal Communication Symposium, IUCS 2009",

note = "3rd International Universal Communication Symposium, IUCS 2009 ; Conference date: 03-12-2009 Through 04-12-2009",

}

TY - GEN

T1 - Topic relatedness in evaluative information extraction

AU - Kawada, Takuya

AU - Nakagawa, Tetsuji

AU - Inui, Kentaro

AU - Kurohashi, Sadao

PY - 2009

Y1 - 2009

N2 - The task of extracting opinions/evaluations related to a given topic from a large number of documents such as Web documents is crucial for developing an automatic evaluation finding system, which can handle a wide variety of topics as input. In this paper, we discuss the topic relatedness of extracted evaluation through analysis of a corpus we developed. We suggest here that the semantic relationship between the target of each extracted evaluation and a given topic helps in judging topic relatedness. In addition, we point out other factors that are beyond the analysis of topic-target relations for judging the topic relatedness of evaluation.

AB - The task of extracting opinions/evaluations related to a given topic from a large number of documents such as Web documents is crucial for developing an automatic evaluation finding system, which can handle a wide variety of topics as input. In this paper, we discuss the topic relatedness of extracted evaluation through analysis of a corpus we developed. We suggest here that the semantic relationship between the target of each extracted evaluation and a given topic helps in judging topic relatedness. In addition, we point out other factors that are beyond the analysis of topic-target relations for judging the topic relatedness of evaluation.

UR - http://www.scopus.com/inward/record.url?scp=76749154535&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=76749154535&partnerID=8YFLogxK

U2 - 10.1145/1667780.1667804

DO - 10.1145/1667780.1667804

M3 - Conference contribution

AN - SCOPUS:76749154535

SN - 9781605586410

T3 - ACM International Conference Proceeding Series

SP - 120

EP - 125

BT - Proceedings of the 3rd International Universal Communication Symposium, IUCS 2009

T2 - 3rd International Universal Communication Symposium, IUCS 2009

Y2 - 3 December 2009 through 4 December 2009

ER -

Topic relatedness in evaluative information extraction

Abstract

Publication series

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this