We describe a system used by the NASA Astrophysics Data System to identify bibliographic references obtained from scanned article pages by OCR methods with records in a bibliographic database. We analyze the process generating the noisy references and conclude that the three-step procedure of correcting the OCR results, parsing the corrected string and matching it against the database provides unsatisfactory results. Instead, we propose a method that allows a controlled merging of correction, parsing and matching, inspired by dependency grammars. We also report on the effectiveness of various heuristics that we have employed to improve recall.
@article{arxiv.cs/0401028,
title = {Automated Resolution of Noisy Bibliographic References},
author = {Markus Demleitner and Michael Kurtz and Alberto Accomazzi and Günther Eichhorn and Carolyn S. Grant and Steven S. Murray},
journal= {arXiv preprint arXiv:cs/0401028},
year = {2007}
}
Comments
10 pages, 1 figure; accepted for publication in the proceedings of the 2004 Meeting of the International Federation of Classification Societies