A corpus-based analysis of coreferential recency effect in Japanese discourse for tracking dynamic topic

Shun Shiramatsu; Tadachika Ozono; Toramatsu Shintani; Hiroshi G. Okuno

doi:10.1109/ICIS.2010.65

A corpus-based analysis of coreferential recency effect in Japanese discourse for tracking dynamic topic

Shun Shiramatsu^*, Tadachika Ozono, Toramatsu Shintani, Hiroshi G. Okuno

^*この研究の対応する著者

研究成果: Conference contribution

1 被引用数 (Scopus)

抄録

This paper describes an analysis of the recency effect of terms appearing in a corpus of meeting transcripts in Japanese. The aim of the study is to improve a method for tracking dynamic topics that have been developed for visualizing a long meeting transcript. The recency effect observed from the appearance of terms in discourse context, the coreferential recency effect, is an important factor to deal with dynamic transition of topic. Statistical analysis using a corpus of meeting transcripts quantitatively clarifies the relationship between linguistic features and the coreferential recency effect.

本文言語	English
ホスト出版物のタイトル	Proceedings - 9th IEEE/ACIS International Conference on Computer and Information Science, ICIS 2010
ページ	645-650
ページ数	6
DOI	https://doi.org/10.1109/ICIS.2010.65
出版ステータス	Published - 2010
外部発表	はい
イベント	9th IEEE/ACIS International Conference on Computer and Information Science, ICIS 2010 - Yamagata 継続期間: 2010 8月 18 → 2010 8月 20

Other

Other	9th IEEE/ACIS International Conference on Computer and Information Science, ICIS 2010
City	Yamagata
Period	10/8/18 → 10/8/20

ASJC Scopus subject areas

情報システム

文献へのアクセス

10.1109/ICIS.2010.65

他のファイルとリンク

引用スタイル

Shiramatsu, S, Ozono, T, Shintani, T & Okuno, HG 2010, A corpus-based analysis of coreferential recency effect in Japanese discourse for tracking dynamic topic. in Proceedings - 9th IEEE/ACIS International Conference on Computer and Information Science, ICIS 2010., 5590983, pp. 645-650, 9th IEEE/ACIS International Conference on Computer and Information Science, ICIS 2010, Yamagata, 10/8/18. https://doi.org/10.1109/ICIS.2010.65

@inproceedings{29d780cd20f8422eb133a387ef1647cf,

title = "A corpus-based analysis of coreferential recency effect in Japanese discourse for tracking dynamic topic",

abstract = "This paper describes an analysis of the recency effect of terms appearing in a corpus of meeting transcripts in Japanese. The aim of the study is to improve a method for tracking dynamic topics that have been developed for visualizing a long meeting transcript. The recency effect observed from the appearance of terms in discourse context, the coreferential recency effect, is an important factor to deal with dynamic transition of topic. Statistical analysis using a corpus of meeting transcripts quantitatively clarifies the relationship between linguistic features and the coreferential recency effect.",

keywords = "Corpus analysis, Discourse analysis, Natural language processing, Salience, Serial position curve",

author = "Shun Shiramatsu and Tadachika Ozono and Toramatsu Shintani and Okuno, {Hiroshi G.}",

year = "2010",

doi = "10.1109/ICIS.2010.65",

language = "English",

isbn = "9780769541471",

pages = "645--650",

booktitle = "Proceedings - 9th IEEE/ACIS International Conference on Computer and Information Science, ICIS 2010",

note = "9th IEEE/ACIS International Conference on Computer and Information Science, ICIS 2010 ; Conference date: 18-08-2010 Through 20-08-2010",

}

TY - GEN

T1 - A corpus-based analysis of coreferential recency effect in Japanese discourse for tracking dynamic topic

AU - Shiramatsu, Shun

AU - Ozono, Tadachika

AU - Shintani, Toramatsu

AU - Okuno, Hiroshi G.

PY - 2010

Y1 - 2010

N2 - This paper describes an analysis of the recency effect of terms appearing in a corpus of meeting transcripts in Japanese. The aim of the study is to improve a method for tracking dynamic topics that have been developed for visualizing a long meeting transcript. The recency effect observed from the appearance of terms in discourse context, the coreferential recency effect, is an important factor to deal with dynamic transition of topic. Statistical analysis using a corpus of meeting transcripts quantitatively clarifies the relationship between linguistic features and the coreferential recency effect.

AB - This paper describes an analysis of the recency effect of terms appearing in a corpus of meeting transcripts in Japanese. The aim of the study is to improve a method for tracking dynamic topics that have been developed for visualizing a long meeting transcript. The recency effect observed from the appearance of terms in discourse context, the coreferential recency effect, is an important factor to deal with dynamic transition of topic. Statistical analysis using a corpus of meeting transcripts quantitatively clarifies the relationship between linguistic features and the coreferential recency effect.

KW - Corpus analysis

KW - Discourse analysis

KW - Natural language processing

KW - Salience

KW - Serial position curve

UR - http://www.scopus.com/inward/record.url?scp=78649258074&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78649258074&partnerID=8YFLogxK

U2 - 10.1109/ICIS.2010.65

DO - 10.1109/ICIS.2010.65

M3 - Conference contribution

AN - SCOPUS:78649258074

SN - 9780769541471

SP - 645

EP - 650

BT - Proceedings - 9th IEEE/ACIS International Conference on Computer and Information Science, ICIS 2010

T2 - 9th IEEE/ACIS International Conference on Computer and Information Science, ICIS 2010

Y2 - 18 August 2010 through 20 August 2010

ER -

A corpus-based analysis of coreferential recency effect in Japanese discourse for tracking dynamic topic

抄録

Other

ASJC Scopus subject areas

文献へのアクセス

他のファイルとリンク

フィンガープリント

引用スタイル