Increasing Recall for Text Re-use in Historical Documents to Support Research in the Humanities. Büchler, M., Crane, G., Moritz, M., & Babeu, A. In Zaphiris, P., Buchanan, G., Rasmussen, E., & Loizides, F., editors, Theory and Practice of Digital Libraries, of Lecture Notes in Computer Science, pages 95–100, Berlin, Heidelberg, 2012. Springer. doi abstract bibtex High precision text re-use detection allows humanists to discover where and how particular authors are quoted (e.g., the different sections of Plato’s work that come in and out of vogue). This paper reports on on-going work to provide the high recall text re-use detection that humanists often demand. Using an edition of one Greek work that marked quotations and paraphrases from the Homeric epics as our testbed, we were able to achieve a recall of at least 94% while maintaining a precision of 73%. This particular study is part of a larger effort to detect text re-use across 15 million words of Greek and 10 million words of Latin available or under development as openly licensed TEI XML.
@inproceedings{buchler_increasing_2012,
address = {Berlin, Heidelberg},
series = {Lecture {Notes} in {Computer} {Science}},
title = {Increasing {Recall} for {Text} {Re}-use in {Historical} {Documents} to {Support} {Research} in the {Humanities}},
isbn = {978-3-642-33290-6},
doi = {10.1007/978-3-642-33290-6_11},
abstract = {High precision text re-use detection allows humanists to discover where and how particular authors are quoted (e.g., the different sections of Plato’s work that come in and out of vogue). This paper reports on on-going work to provide the high recall text re-use detection that humanists often demand. Using an edition of one Greek work that marked quotations and paraphrases from the Homeric epics as our testbed, we were able to achieve a recall of at least 94\% while maintaining a precision of 73\%. This particular study is part of a larger effort to detect text re-use across 15 million words of Greek and 10 million words of Latin available or under development as openly licensed TEI XML.},
language = {en},
booktitle = {Theory and {Practice} of {Digital} {Libraries}},
publisher = {Springer},
author = {Büchler, Marco and Crane, Gregory and Moritz, Maria and Babeu, Alison},
editor = {Zaphiris, Panayiotis and Buchanan, George and Rasmussen, Edie and Loizides, Fernando},
year = {2012},
keywords = {Athenaeus, Homer, historical text re-use, hypertextuality},
pages = {95--100},
}
Downloads: 0
{"_id":"43PdYpZcTvSKEdsgp","bibbaseid":"bchler-crane-moritz-babeu-increasingrecallfortextreuseinhistoricaldocumentstosupportresearchinthehumanities-2012","author_short":["Büchler, M.","Crane, G.","Moritz, M.","Babeu, A."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","address":"Berlin, Heidelberg","series":"Lecture Notes in Computer Science","title":"Increasing Recall for Text Re-use in Historical Documents to Support Research in the Humanities","isbn":"978-3-642-33290-6","doi":"10.1007/978-3-642-33290-6_11","abstract":"High precision text re-use detection allows humanists to discover where and how particular authors are quoted (e.g., the different sections of Plato’s work that come in and out of vogue). This paper reports on on-going work to provide the high recall text re-use detection that humanists often demand. Using an edition of one Greek work that marked quotations and paraphrases from the Homeric epics as our testbed, we were able to achieve a recall of at least 94% while maintaining a precision of 73%. This particular study is part of a larger effort to detect text re-use across 15 million words of Greek and 10 million words of Latin available or under development as openly licensed TEI XML.","language":"en","booktitle":"Theory and Practice of Digital Libraries","publisher":"Springer","author":[{"propositions":[],"lastnames":["Büchler"],"firstnames":["Marco"],"suffixes":[]},{"propositions":[],"lastnames":["Crane"],"firstnames":["Gregory"],"suffixes":[]},{"propositions":[],"lastnames":["Moritz"],"firstnames":["Maria"],"suffixes":[]},{"propositions":[],"lastnames":["Babeu"],"firstnames":["Alison"],"suffixes":[]}],"editor":[{"propositions":[],"lastnames":["Zaphiris"],"firstnames":["Panayiotis"],"suffixes":[]},{"propositions":[],"lastnames":["Buchanan"],"firstnames":["George"],"suffixes":[]},{"propositions":[],"lastnames":["Rasmussen"],"firstnames":["Edie"],"suffixes":[]},{"propositions":[],"lastnames":["Loizides"],"firstnames":["Fernando"],"suffixes":[]}],"year":"2012","keywords":"Athenaeus, Homer, historical text re-use, hypertextuality","pages":"95–100","bibtex":"@inproceedings{buchler_increasing_2012,\n\taddress = {Berlin, Heidelberg},\n\tseries = {Lecture {Notes} in {Computer} {Science}},\n\ttitle = {Increasing {Recall} for {Text} {Re}-use in {Historical} {Documents} to {Support} {Research} in the {Humanities}},\n\tisbn = {978-3-642-33290-6},\n\tdoi = {10.1007/978-3-642-33290-6_11},\n\tabstract = {High precision text re-use detection allows humanists to discover where and how particular authors are quoted (e.g., the different sections of Plato’s work that come in and out of vogue). This paper reports on on-going work to provide the high recall text re-use detection that humanists often demand. Using an edition of one Greek work that marked quotations and paraphrases from the Homeric epics as our testbed, we were able to achieve a recall of at least 94\\% while maintaining a precision of 73\\%. This particular study is part of a larger effort to detect text re-use across 15 million words of Greek and 10 million words of Latin available or under development as openly licensed TEI XML.},\n\tlanguage = {en},\n\tbooktitle = {Theory and {Practice} of {Digital} {Libraries}},\n\tpublisher = {Springer},\n\tauthor = {Büchler, Marco and Crane, Gregory and Moritz, Maria and Babeu, Alison},\n\teditor = {Zaphiris, Panayiotis and Buchanan, George and Rasmussen, Edie and Loizides, Fernando},\n\tyear = {2012},\n\tkeywords = {Athenaeus, Homer, historical text re-use, hypertextuality},\n\tpages = {95--100},\n}\n\n\n\n","author_short":["Büchler, M.","Crane, G.","Moritz, M.","Babeu, A."],"editor_short":["Zaphiris, P.","Buchanan, G.","Rasmussen, E.","Loizides, F."],"key":"buchler_increasing_2012","id":"buchler_increasing_2012","bibbaseid":"bchler-crane-moritz-babeu-increasingrecallfortextreuseinhistoricaldocumentstosupportresearchinthehumanities-2012","role":"author","urls":{},"keyword":["Athenaeus","Homer","historical text re-use","hypertextuality"],"metadata":{"authorlinks":{}}},"bibtype":"inproceedings","biburl":"https://bibbase.org/zotero-group/schulzkx/5158478","dataSources":["JFDnASMkoQCjjGL8E"],"keywords":["athenaeus","homer","historical text re-use","hypertextuality"],"search_terms":["increasing","recall","text","use","historical","documents","support","research","humanities","büchler","crane","moritz","babeu"],"title":"Increasing Recall for Text Re-use in Historical Documents to Support Research in the Humanities","year":2012}