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.
| Original language | English |
|---|---|
| Title of host publication | Proceedings - 9th IEEE/ACIS International Conference on Computer and Information Science, ICIS 2010 |
| Pages | 645-650 |
| Number of pages | 6 |
| DOIs | |
| Publication status | Published - 2010 |
| Externally published | Yes |
| Event | 9th IEEE/ACIS International Conference on Computer and Information Science, ICIS 2010 - Yamagata Duration: 2010 Aug 18 → 2010 Aug 20 |
Other
| Other | 9th IEEE/ACIS International Conference on Computer and Information Science, ICIS 2010 |
|---|---|
| City | Yamagata |
| Period | 10/8/18 → 10/8/20 |
Fingerprint
Keywords
- Corpus analysis
- Discourse analysis
- Natural language processing
- Salience
- Serial position curve
ASJC Scopus subject areas
- Information Systems
Cite this
A corpus-based analysis of coreferential recency effect in Japanese discourse for tracking dynamic topic. / Shiramatsu, Shun; Ozono, Tadachika; Shintani, Toramatsu; Okuno, Hiroshi G.
Proceedings - 9th IEEE/ACIS International Conference on Computer and Information Science, ICIS 2010. 2010. p. 645-650 5590983.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
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
SN - 9780769541471
SP - 645
EP - 650
BT - Proceedings - 9th IEEE/ACIS International Conference on Computer and Information Science, ICIS 2010
ER -