%0 Conference Paper %1 sautter2012improved %A Sautter, Guido %A Böhm, Klemens %B Proceedings of the Second International Conference on Theory and Practice of Digital Libraries %C Berlin/Heidelberg %D 2012 %I Springer %K bibliographic extraction ie information parsing reference %P 370--382 %R 10.1007/978-3-642-33290-6_40 %T Improved Bibliographic Reference Parsing Based on Repeated Patterns %U http://dx.doi.org/10.1007/978-3-642-33290-6_40 %X Parsing details like author names and titles out of bibliographic references of scientific publications is an important issue. However, most existing techniques are tailored to the highly standardized reference styles used in the last two to three decades. Their performance tends to degrade when faced with the wider variety of reference styles used in older, historic publications. Thus, existing techniques are of limited use when creating comprehensive bibliographies covering both historic and contemporary scientific publications. This paper presents RefParse, a generic approach to bibliographic reference parsing that is independent of any specific reference style. Its core feature is an inference mechanism that exploits the regularities inherent in any list of references to deduce its format. Our evaluation shows that RefParse outperforms existing parsers both for contemporary and for historic reference lists. %@ 978-3-642-33289-0

@inproceedings{sautter2012improved, abstract = {Parsing details like author names and titles out of bibliographic references of scientific publications is an important issue. However, most existing techniques are tailored to the highly standardized reference styles used in the last two to three decades. Their performance tends to degrade when faced with the wider variety of reference styles used in older, historic publications. Thus, existing techniques are of limited use when creating comprehensive bibliographies covering both historic and contemporary scientific publications. This paper presents RefParse, a generic approach to bibliographic reference parsing that is independent of any specific reference style. Its core feature is an inference mechanism that exploits the regularities inherent in any list of references to deduce its format. Our evaluation shows that RefParse outperforms existing parsers both for contemporary and for historic reference lists.}, acmid = {2403883}, added-at = {2014-03-05T11:45:36.000+0100}, address = {Berlin/Heidelberg}, author = {Sautter, Guido and Böhm, Klemens}, biburl = {https://www.bibsonomy.org/bibtex/2bc703f2b11ae12881a649675649e2c10/jaeschke}, booktitle = {Proceedings of the Second International Conference on Theory and Practice of Digital Libraries}, doi = {10.1007/978-3-642-33290-6_40}, interhash = {6ee58c546bbb92cff6bf96ab33c1a5e6}, intrahash = {bc703f2b11ae12881a649675649e2c10}, isbn = {978-3-642-33289-0}, keywords = {bibliographic extraction ie information parsing reference}, location = {Paphos, Cyprus}, numpages = {13}, pages = {370--382}, publisher = {Springer}, series = {TPDL'12}, timestamp = {2014-07-28T15:57:31.000+0200}, title = {Improved Bibliographic Reference Parsing Based on Repeated Patterns}, url = {http://dx.doi.org/10.1007/978-3-642-33290-6_40}, year = 2012 }