@inproceedings{15fb3b1c743f4fb990d2ae1664818804,
title = "A web service for scholarly big data information extraction",
abstract = "The automatic extraction of metadata and other information from scholarly documents is a common task in academic digital libraries, search engines, and document management systems to allow for the management and categorization of documents and for search to take place. A Web-accessible API can simplify this extraction by providing a single point of operation for extraction that can be incorporated into multiple document workflows without the need for each workflow to implement and support its own extraction functionality. In this paper, we describe CiteSeerExtractor, a RESTful API for scholarly information extraction that exploits the fact that there is duplication in scholarly big data and makes use of a near duplicate matching backend. The backend stores previously extracted metadata and avoids extracting metadata from a document if it has already been extracted before. We describe the design, implementation, and functionality of CiteSeerExtractor and show how the duplicate document matching results in a difference of 8.46% in the time required to extract header and citation information from approximately 3.5 million documents compared to a baseline.",
author = "Kyle Williams and Lichi Li and Madian Khabsa and Jian Wu and Shih, {Patrick C.} and Giles, {C. Lee}",
note = "Publisher Copyright: {\textcopyright} 2014 IEEE.; 2014 21st IEEE International Conference on Web Services, ICWS 2014 ; Conference date: 27-06-2014 Through 02-07-2014",
year = "2014",
doi = "10.1109/ICWS.2014.27",
language = "English (US)",
series = "Proceedings - 2014 IEEE International Conference on Web Services, ICWS 2014",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "105--112",
editor = "{De Roure}, David and Bhavani Thuraisingham and Jia Zhang",
booktitle = "Proceedings - 2014 IEEE International Conference on Web Services, ICWS 2014",
address = "United States",
}