@inproceedings{e916d0133179444e9176165dcd800b1f,
title = "CRF-based bibliography extraction from reference strings focusing on various token granularities",
abstract = "The references of academic articles include important bibliographic elements such as authors' names and article titles. Automatic extraction of these elements is useful because they can be used for various purposes, including searching. In this paper, a method for automatically extracting bibliographic elements from the text of reference strings is proposed. The proposed method assigns bibliographic labels to reference strings by using linguistic information and conditional random fields. Experimental results indicated that the extraction accuracies of major bibliographies were more than 96%.",
keywords = "bibliography extraction, conditional random field (CRF), delimiter, reference, tokenization",
author = "Manabu Ohta and Daiki Arauchi and Atsuhiro Takasu and Jun Adachi",
year = "2012",
doi = "10.1109/DAS.2012.28",
language = "English",
isbn = "9780769546612",
series = "Proceedings - 10th IAPR International Workshop on Document Analysis Systems, DAS 2012",
pages = "276--281",
booktitle = "Proceedings - 10th IAPR International Workshop on Document Analysis Systems, DAS 2012",
note = "10th IAPR International Workshop on Document Analysis Systems, DAS 2012 ; Conference date: 27-03-2012 Through 29-03-2012",
}