When printed hypertexts go digital: information extraction from the parsing of indices Export

@inproceedings{citeulike:5043040, abstract = {Modern critical editions of ancient works generally include manually created indices of other sources quoted in the text. Since indices can be considered as a form of domain specific language, the paper presents a parsing-based approach to the problem of extracting information from them to support the creation of a collection of fragmentary texts. This paper first considers the characteristics and structure of quotation indices and their importance when dealing with fragmentary texts. It then presents the results of applying a fuzzy parser to the OCR transcription of an index of quotations to extract information from potentially noisy input.}, address = {New York, NY, USA}, author = {Romanello, Matteo and Berti, Monica and Babeu, Alison and Crane, Gregory}, booktitle = {HT '09: Proceedings of the 20th ACM conference on Hypertext and hypermedia}, citeulike-article-id = {5043040}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1557914.1557987}, citeulike-linkout-1 = {http://dx.doi.org/10.1145/1557914.1557987}, doi = {10.1145/1557914.1557987}, isbn = {978-1-60558-486-7}, keywords = {digital-classics, ocr, ontologies--domain}, location = {Torino, Italy}, pages = {357--358}, posted-at = {2009-07-02 18:15:48}, priority = {0}, publisher = {ACM}, title = {When printed hypertexts go digital: information extraction from the parsing of indices}, url = {http://dx.doi.org/10.1145/1557914.1557987}, year = {2009} }

TY - CONF ID - citeulike:5043040 L3 - citeulike-article-id:5043040 N2 - Modern critical editions of ancient works generally include manually created indices of other sources quoted in the text. Since indices can be considered as a form of domain specific language, the paper presents a parsing-based approach to the problem of extracting information from them to support the creation of a collection of fragmentary texts. This paper first considers the characteristics and structure of quotation indices and their importance when dealing with fragmentary texts. It then presents the results of applying a fuzzy parser to the OCR transcription of an index of quotations to extract information from potentially noisy input. CY - Torino, Italy SN - 978-1-60558-486-7 AD - New York, NY, USA EP - 358 TI - When printed hypertexts go digital: information extraction from the parsing of indices PB - ACM T2 - HT '09: Proceedings of the 20th ACM conference on Hypertext and hypermedia SP - 357 KW - digital-classics KW - ocr KW - ontologies--domain AU - Romanello, Matteo AU - Berti, Monica AU - Babeu, Alison AU - Crane, Gregory PY - 2009/// UR - http://dx.doi.org/10.1145/1557914.1557987 ER -