A Corpus-Based Analysis of Coreferential Recency Effect in Japanese Discourse for Tracking Dynamic Topic

Author

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

Author_Institution

Dept. of Comput. Sci. & Eng., Nagoya Inst. of Technol., Nagoya, Japan

fYear

2010

fDate

18-20 Aug. 2010

Firstpage

645

Lastpage

650

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

linguistics; natural language processing; statistical analysis; Japanese discourse; coreferential recency effect; corpus-based analysis; dynamic topic tracking; linguistic features; meeting transcripts visualization; statistical analysis; Color; Conferences; Fitting; Information science; Nickel; Position measurement; Weight measurement; corpus analysis; discourse analysis; natural language processing; salience; serial position curve;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer and Information Science (ICIS), 2010 IEEE/ACIS 9th International Conference on

Conference_Location

Yamagata

Print_ISBN

978-1-4244-8198-9

Type

conf

DOI

10.1109/ICIS.2010.65

Filename

5590983