@inproceedings{41319c74726341d894887c1e0708d1c3,
title = "Detecting academic papers on the web",
abstract = "Our research goal is to develop a search engine for open access to academic papers. English and Japanese test sets were built for detection of academic papers from 20,000 PDF files in each language using five annotators. Six classifiers were trained using similar features for each language. We report F1 of 0.74 for English and 0.54 for Japanese and argue that similar features could easily be generated for other languages as well.",
keywords = "academic papers, pdf, search engine",
author = "Emi Ishita and Teru Agata and Atsushi Ikeuchi and Miyata Yosuke and Shuichi Ueda",
year = "2011",
doi = "10.1145/1998076.1998161",
language = "English",
isbn = "9781450307444",
series = "Proceedings of the ACM/IEEE Joint Conference on Digital Libraries",
pages = "413--414",
booktitle = "JCDL'11 - Proceedings of the 2011 ACM/IEEE Joint Conference on Digital Libraries",
note = "11th Annual International ACM/IEEE Joint Conference on Digital Libraries, JCDL'11 ; Conference date: 13-06-2011 Through 17-06-2011",
}