%0 Conference Paper %1 romanello2009printed %A Romanello, Matteo %A Berti, Monica %A Babeu, Alison %A Crane, Gregory %B HT '09: Proceedings of the Twentieth ACM Conference on Hypertext and Hypermedia %C New York, NY, USA %D 2009 %I ACM %K extraction ht2009 hypertexts indices information parsing poster pp159 printed %T When Printed Hypertexts Go Digital: Information Extraction from the Parsing of Indices %X 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 speci
c 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
rst 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.

@inproceedings{romanello2009printed, 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 speci
c 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
rst 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.}, added-at = {2009-06-16T15:00:02.000+0200}, address = {New York, NY, USA}, author = {Romanello, Matteo and Berti, Monica and Babeu, Alison and Crane, Gregory}, biburl = {https://www.bibsonomy.org/bibtex/278dc574ec491997f63bafda3f37b8006/ht09}, booktitle = {HT '09: Proceedings of the Twentieth ACM Conference on Hypertext and Hypermedia}, interhash = {d69e2ace20fdb0ef9e43dbf6b16a5f33}, intrahash = {78dc574ec491997f63bafda3f37b8006}, keywords = {extraction ht2009 hypertexts indices information parsing poster pp159 printed}, month = {July}, paperid = {pp159}, publisher = {ACM}, session = {Poster}, timestamp = {2009-06-16T15:00:07.000+0200}, title = {When Printed Hypertexts Go Digital: Information Extraction from the Parsing of Indices}, year = 2009 }