@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",
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",
note = "12th International Conference on Digital Information Management, ICDIM 2017 ; Conference date: 12-09-2017 Through 14-09-2017",
}