Feature extraction using restricted bootstrapping

Sachio Hirokawa

doi:10.1109/ICIS.2012.50

Feature extraction using restricted bootstrapping

Sachio Hirokawa

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

2 Citations (Scopus)

Abstract

The bootstrapping method is known as an application of the Page-rank technique for documents and words. The technique calculates the score of the words by mutually propagating the score of the words and the documents. However, sometimes the result is far away from the initial query word. The problem is known as "topic drift". This paper proposes to restrict the words to be to the top t words in the process of bootstrapping. The method is simpler than the technique known so far. The method is applied for the real bankruptcy information documents to extract the bankruptcy causes strongly related to the query. It is confirmed that the method prevents the topic drift.

Original language	English
Title of host publication	Proceedings - 2012 IEEE/ACIS 11th International Conference on Computer and Information Science, ICIS 2012
Pages	283-288
Number of pages	6
DOIs	https://doi.org/10.1109/ICIS.2012.50
Publication status	Published - 2012
Event	2012 IEEE/ACIS 11th International Conference on Computer and Information Science, ICIS 2012 - Shanghai, China Duration: May 30 2012 → Jun 1 2012

Publication series

Name	Proceedings - 2012 IEEE/ACIS 11th International Conference on Computer and Information Science, ICIS 2012

Other

Other	2012 IEEE/ACIS 11th International Conference on Computer and Information Science, ICIS 2012
Country/Territory	China
City	Shanghai
Period	5/30/12 → 6/1/12

All Science Journal Classification (ASJC) codes

Computer Networks and Communications
Information Systems

Access to Document

10.1109/ICIS.2012.50

Cite this

Feature extraction using restricted bootstrapping. / Hirokawa, Sachio.
Proceedings - 2012 IEEE/ACIS 11th International Conference on Computer and Information Science, ICIS 2012. 2012. p. 283-288 6211110 (Proceedings - 2012 IEEE/ACIS 11th International Conference on Computer and Information Science, ICIS 2012).

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

Hirokawa, S 2012, Feature extraction using restricted bootstrapping. in Proceedings - 2012 IEEE/ACIS 11th International Conference on Computer and Information Science, ICIS 2012., 6211110, Proceedings - 2012 IEEE/ACIS 11th International Conference on Computer and Information Science, ICIS 2012, pp. 283-288, 2012 IEEE/ACIS 11th International Conference on Computer and Information Science, ICIS 2012, Shanghai, China, 5/30/12. https://doi.org/10.1109/ICIS.2012.50

@inproceedings{5e7fc1947ca342e1b4c5463d0b324dd8,

title = "Feature extraction using restricted bootstrapping",

abstract = "The bootstrapping method is known as an application of the Page-rank technique for documents and words. The technique calculates the score of the words by mutually propagating the score of the words and the documents. However, sometimes the result is far away from the initial query word. The problem is known as {"}topic drift{"}. This paper proposes to restrict the words to be to the top t words in the process of bootstrapping. The method is simpler than the technique known so far. The method is applied for the real bankruptcy information documents to extract the bankruptcy causes strongly related to the query. It is confirmed that the method prevents the topic drift.",

author = "Sachio Hirokawa",

year = "2012",

doi = "10.1109/ICIS.2012.50",

language = "English",

isbn = "9780769546940",

series = "Proceedings - 2012 IEEE/ACIS 11th International Conference on Computer and Information Science, ICIS 2012",

pages = "283--288",

booktitle = "Proceedings - 2012 IEEE/ACIS 11th International Conference on Computer and Information Science, ICIS 2012",

note = "2012 IEEE/ACIS 11th International Conference on Computer and Information Science, ICIS 2012 ; Conference date: 30-05-2012 Through 01-06-2012",

}

TY - GEN

T1 - Feature extraction using restricted bootstrapping

AU - Hirokawa, Sachio

PY - 2012

Y1 - 2012

N2 - The bootstrapping method is known as an application of the Page-rank technique for documents and words. The technique calculates the score of the words by mutually propagating the score of the words and the documents. However, sometimes the result is far away from the initial query word. The problem is known as "topic drift". This paper proposes to restrict the words to be to the top t words in the process of bootstrapping. The method is simpler than the technique known so far. The method is applied for the real bankruptcy information documents to extract the bankruptcy causes strongly related to the query. It is confirmed that the method prevents the topic drift.

AB - The bootstrapping method is known as an application of the Page-rank technique for documents and words. The technique calculates the score of the words by mutually propagating the score of the words and the documents. However, sometimes the result is far away from the initial query word. The problem is known as "topic drift". This paper proposes to restrict the words to be to the top t words in the process of bootstrapping. The method is simpler than the technique known so far. The method is applied for the real bankruptcy information documents to extract the bankruptcy causes strongly related to the query. It is confirmed that the method prevents the topic drift.

UR - http://www.scopus.com/inward/record.url?scp=84864051520&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84864051520&partnerID=8YFLogxK

U2 - 10.1109/ICIS.2012.50

DO - 10.1109/ICIS.2012.50

M3 - Conference contribution

AN - SCOPUS:84864051520

SN - 9780769546940

T3 - Proceedings - 2012 IEEE/ACIS 11th International Conference on Computer and Information Science, ICIS 2012

SP - 283

EP - 288

BT - Proceedings - 2012 IEEE/ACIS 11th International Conference on Computer and Information Science, ICIS 2012

T2 - 2012 IEEE/ACIS 11th International Conference on Computer and Information Science, ICIS 2012

Y2 - 30 May 2012 through 1 June 2012

ER -

Feature extraction using restricted bootstrapping

Abstract

Publication series

Other

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this