CRF-based bibliography extraction from reference strings using a small amount of training data

Daiki Namikoshi; Manabu Ohta; Atsuhiro Takasu; Jun Adachi

doi:10.1109/ICDIM.2017.8244665

CRF-based bibliography extraction from reference strings using a small amount of training data

Daiki Namikoshi, Manabu Ohta, Atsuhiro Takasu, Jun Adachi

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

1 Citation (Scopus)

Abstract

The effective use of digital libraries demands maintenance of bibliographic databases. Useful bibliographic information appears in the reference fields of academic papers, so we are developing a method for automatic extraction of bibliographic information from reference strings using a conditional random field (CRF). However, at least a few hundred reference strings are necessary to learn an accurate CRF. In this paper, we propose active learning and transfer learning techniques to reduce the required training data for CRFs. We evaluate extraction accuracies and the associated training cost by experiments.

Original language	English
Title of host publication	2017 12th International Conference on Digital Information Management, ICDIM 2017
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	59-64
Number of pages	6
ISBN (Electronic)	9781538606643
DOIs	https://doi.org/10.1109/ICDIM.2017.8244665
Publication status	Published - Jun 28 2017
Event	12th International Conference on Digital Information Management, ICDIM 2017 - Fukuoka, Japan Duration: Sept 12 2017 → Sept 14 2017

Publication series

Name	2017 12th International Conference on Digital Information Management, ICDIM 2017
Volume	2018-January

Other

Other	12th International Conference on Digital Information Management, ICDIM 2017
Country/Territory	Japan
City	Fukuoka
Period	9/12/17 → 9/14/17

Keywords

CRF
active learning
bibliography extraction
confidence measure
transfer learning

ASJC Scopus subject areas

Computer Networks and Communications
Information Systems
Information Systems and Management

Access to Document

10.1109/ICDIM.2017.8244665

Cite this

Namikoshi, D., Ohta, M., Takasu, A., & Adachi, J. (2017). CRF-based bibliography extraction from reference strings using a small amount of training data. In 2017 12th International Conference on Digital Information Management, ICDIM 2017 (pp. 59-64). (2017 12th International Conference on Digital Information Management, ICDIM 2017; Vol. 2018-January). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICDIM.2017.8244665

CRF-based bibliography extraction from reference strings using a small amount of training data. / Namikoshi, Daiki; Ohta, Manabu; Takasu, Atsuhiro et al.
2017 12th International Conference on Digital Information Management, ICDIM 2017. Institute of Electrical and Electronics Engineers Inc., 2017. p. 59-64 (2017 12th International Conference on Digital Information Management, ICDIM 2017; Vol. 2018-January).

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

Namikoshi, D, Ohta, M, Takasu, A & Adachi, J 2017, CRF-based bibliography extraction from reference strings using a small amount of training data. in 2017 12th International Conference on Digital Information Management, ICDIM 2017. 2017 12th International Conference on Digital Information Management, ICDIM 2017, vol. 2018-January, Institute of Electrical and Electronics Engineers Inc., pp. 59-64, 12th International Conference on Digital Information Management, ICDIM 2017, Fukuoka, Japan, 9/12/17. https://doi.org/10.1109/ICDIM.2017.8244665

Namikoshi D, Ohta M, Takasu A, Adachi J. CRF-based bibliography extraction from reference strings using a small amount of training data. In 2017 12th International Conference on Digital Information Management, ICDIM 2017. Institute of Electrical and Electronics Engineers Inc. 2017. p. 59-64. (2017 12th International Conference on Digital Information Management, ICDIM 2017). doi: 10.1109/ICDIM.2017.8244665

Namikoshi, Daiki ; Ohta, Manabu ; Takasu, Atsuhiro et al. / CRF-based bibliography extraction from reference strings using a small amount of training data. 2017 12th International Conference on Digital Information Management, ICDIM 2017. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 59-64 (2017 12th International Conference on Digital Information Management, ICDIM 2017).

@inproceedings{45bd13ce172642408dbbd93465a150ec,

title = "CRF-based bibliography extraction from reference strings using a small amount of training data",

abstract = "The effective use of digital libraries demands maintenance of bibliographic databases. Useful bibliographic information appears in the reference fields of academic papers, so we are developing a method for automatic extraction of bibliographic information from reference strings using a conditional random field (CRF). However, at least a few hundred reference strings are necessary to learn an accurate CRF. In this paper, we propose active learning and transfer learning techniques to reduce the required training data for CRFs. We evaluate extraction accuracies and the associated training cost by experiments.",

keywords = "CRF, active learning, bibliography extraction, confidence measure, transfer learning",

author = "Daiki Namikoshi and Manabu Ohta and Atsuhiro Takasu and Jun Adachi",

note = "Publisher Copyright: {\textcopyright} 2017 IEEE.; 12th International Conference on Digital Information Management, ICDIM 2017 ; Conference date: 12-09-2017 Through 14-09-2017",

year = "2017",

month = jun,

day = "28",

doi = "10.1109/ICDIM.2017.8244665",

language = "English",

series = "2017 12th International Conference on Digital Information Management, ICDIM 2017",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "59--64",

booktitle = "2017 12th International Conference on Digital Information Management, ICDIM 2017",

}

TY - GEN

T1 - CRF-based bibliography extraction from reference strings using a small amount of training data

AU - Namikoshi, Daiki

AU - Ohta, Manabu

AU - Takasu, Atsuhiro

AU - Adachi, Jun

PY - 2017/6/28

Y1 - 2017/6/28

N2 - The effective use of digital libraries demands maintenance of bibliographic databases. Useful bibliographic information appears in the reference fields of academic papers, so we are developing a method for automatic extraction of bibliographic information from reference strings using a conditional random field (CRF). However, at least a few hundred reference strings are necessary to learn an accurate CRF. In this paper, we propose active learning and transfer learning techniques to reduce the required training data for CRFs. We evaluate extraction accuracies and the associated training cost by experiments.

AB - The effective use of digital libraries demands maintenance of bibliographic databases. Useful bibliographic information appears in the reference fields of academic papers, so we are developing a method for automatic extraction of bibliographic information from reference strings using a conditional random field (CRF). However, at least a few hundred reference strings are necessary to learn an accurate CRF. In this paper, we propose active learning and transfer learning techniques to reduce the required training data for CRFs. We evaluate extraction accuracies and the associated training cost by experiments.

KW - CRF

KW - active learning

KW - bibliography extraction

KW - confidence measure

KW - transfer learning

UR - http://www.scopus.com/inward/record.url?scp=85049371656&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85049371656&partnerID=8YFLogxK

U2 - 10.1109/ICDIM.2017.8244665

DO - 10.1109/ICDIM.2017.8244665

M3 - Conference contribution

AN - SCOPUS:85049371656

T3 - 2017 12th International Conference on Digital Information Management, ICDIM 2017

SP - 59

EP - 64

BT - 2017 12th International Conference on Digital Information Management, ICDIM 2017

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 12th International Conference on Digital Information Management, ICDIM 2017

Y2 - 12 September 2017 through 14 September 2017

ER -

CRF-based bibliography extraction from reference strings using a small amount of training data

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this