{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T04:31:50Z","timestamp":1779337910006,"version":"3.51.4"},"publisher-location":"Cham","reference-count":45,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319126548","type":"print"},{"value":"9783319126555","type":"electronic"}],"license":[{"start":{"date-parts":[[2014,1,1]],"date-time":"2014-01-01T00:00:00Z","timestamp":1388534400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2014,1,1]],"date-time":"2014-01-01T00:00:00Z","timestamp":1388534400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014]]},"DOI":"10.1007\/978-3-319-12655-5_11","type":"book-chapter","created":{"date-parts":[[2014,12,19]],"date-time":"2014-12-19T15:10:38Z","timestamp":1419001838000},"page":"221-238","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Towards a Historical Text Re-use Detection"],"prefix":"10.1007","author":[{"given":"Marco","family":"B\u00fcchler","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Philip R.","family":"Burns","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Martin","family":"M\u00fcller","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Emily","family":"Franzini","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Greta","family":"Franzini","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2014,12,13]]},"reference":[{"key":"11_CR1","doi-asserted-by":"crossref","unstructured":"Allan J (2002) Topic detection and tracking: event-based information organization. Kluwer International Series on Information Retrieval. Kluwer Academic. ISBN: 9780792376644. http:\/\/books.google.de\/books?id=50hnLI_Jz3cC","DOI":"10.1007\/978-1-4615-0933-2"},{"key":"11_CR2","unstructured":"Basile C, Esposti MD, Rosso\u00a0P, Barr\u00f3n-Cede\u00f1o A (2010) Word length n-grams for text re-use detection. In: Proceedings of the 11th international conference on Computational Linguistics and Intelligent Text Processing, CICLing\u201910. Springer, Berlin\/Heidelberg, pp\u00a0687\u2013699. ISBN: 3-642-12115-2, 978-3-642-12115-9"},{"key":"11_CR3","unstructured":"Believers Resource (2011) XML encoded versions of several English language Bible translations. http:\/\/www.believersresource.com\/categories\/bible-raw-data.html. Accessed 11 Nov 2011"},{"key":"11_CR4","doi-asserted-by":"publisher","unstructured":"Bernstein Y, Croft WB, Moffat A, Zobel\u00a0J, Metzler D (2005) Similarity measures for tracking information flow. In: Proceedings of the 14th ACM international conference on information and knowledge management, CIKM \u201905. ACM, New York, pp\u00a0517\u2013524. doi:10.1145\/1099554.1099695. ISBN: 1-59593-140-6. http:\/\/doi.acm.org\/10.1145\/1099554.1099695","DOI":"10.1145\/1099554.1099695"},{"key":"11_CR5","doi-asserted-by":"publisher","unstructured":"Blei DM, Lafferty JD (2006) Dynamic topic models. In: Proceedings of the 23rd international conference on Machine learning, ICML \u201906, ACM, New York, pp\u00a0113\u2013120. ISBN: 1-59593-383-2. doi:10.1145\/1143844.1143859. http:\/\/doi.acm.org\/10.1145\/1143844.1143859","DOI":"10.1145\/1143844.1143859"},{"key":"11_CR6","series-title":"Lecture Notes in Computer Science, vol","isbn-type":"print","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1007\/978-3-642-24583-1_3","volume-title":"String Processing and Information Retrieval","author":"M Bonzanini","year":"2011","unstructured":"Bonzanini M, Roelleke\u00a0T, Yahyaei S (2011) Cross-lingual text fragment alignment using divergence from randomness. In: Grossi R, Sebastiani F, Silvestri F (eds) String Processing and Information Retrieval, Lecture Notes in Computer Science, vol 7024, pp\u00a014\u201325. ISBN: 978-3-642-24582-4","ISBN":"https:\/\/id.crossref.org\/isbn\/9783642245824"},{"key":"11_CR7","unstructured":"Bordag S (2007) Elements of Knowledge-free and Unsupervised Lexical Acquisition. Ph.D. thesis, Universit\u00e4t Leipzig"},{"key":"11_CR8","unstructured":"Brockett\u00a0C, Dolan WB (2005) Automatically constructing a corpus of sentential paraphrases. In: Third International Workshop on Paraphrasing (IWP2005). Asia Federation of Natural Language Processing. http:\/\/research.microsoft.com\/apps\/pubs\/default.aspx?id=101076"},{"key":"11_CR9","unstructured":"Broder AZ (1997) On the resemblance and containment of documents. In: In compression and complexity of sequences (SEQUENCES97. IEEE Computer Society, Los Alamitos, pp\u00a021\u201329"},{"key":"11_CR10","first-page":"84","volume-title":"Semantic duplicate identification with parsing and machine learning","author":"TVD Br\u00fcck","year":"2010","unstructured":"Br\u00fcck TVD, Eichhorn\u00a0C, Hartrumpf S (2010) Semantic duplicate identification with parsing and machine learning. In: TSD, pp\u00a084\u201392"},{"key":"11_CR11","unstructured":"B\u00fcchler M (2013) Informationstechnische aspekte des historischen text re-use. Ph.D. thesis, Leipzig University, Germany"},{"key":"11_CR12","volume-title":"(2011) Aspects of an infrastructure for eHumanities","author":"M B\u00fcchler","year":"2011","unstructured":"B\u00fcchler M, Boehlke\u00a0V, Heyer G (2011) Aspects of an infrastructure for eHumanities. In: Proceedings of Supporting Digital Humanities 2011"},{"key":"11_CR13","unstructured":"B\u00fcchler M, Scheuermann\u00a0G, J\u00e4nicke S (2014) Visualizations for text re-use. In: Proceedings of the 5th International Conference on Information Visualization Theory and Applications, IVAPP 2014"},{"key":"11_CR14","unstructured":"Burns P (2012) MorphAdorner. http:\/\/morphadorner.northwestern.edu\/. Accessed 1 Nov 2012"},{"key":"11_CR15","unstructured":"Burns PR, Crane G, Mueller M, Heyer\u00a0G, B\u00fcchler M (2011) One step closer to paraphrase detection on historical texts: about the quality of text re-use techniques and the ability to learn paradigmatic relations. In: Proceedings of the 2011 Chicago Colloquium on Digital Humanities and Computer Science, Chicago, 2012"},{"key":"11_CR16","doi-asserted-by":"crossref","unstructured":"Charikar M (2002) Similarity estimation techniques from rounding algorithms. In: John HR (ed) STOC. ACM, New York, pp\u00a0380\u2013388. ISBN: 1-58113-495-9","DOI":"10.1145\/509907.509965"},{"key":"11_CR17","unstructured":"Charikar M, Frieze AM, Mitzenmacher\u00a0M, Broder AZ (1998) Min-wise independent permutations. J Comput Syst Sci 60:327\u2013336. http:\/\/citeseerx.ist.psu.edu\/viewdoc\/summary?doi=10.1.1.121.8215"},{"key":"11_CR18","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1109\/BigData.2013.6691675","volume-title":"Infectious texts: Modeling text reuse in nineteenth-century newspapers","author":"R Cordell","year":"2013","unstructured":"Cordell R, Dillon\u00a0EM, Smith DA (2013) Infectious texts: Modeling text reuse in nineteenth-century newspapers. In: IEEE International Conference on Big Data, pp\u00a086\u201394. doi:10.1109\/BigData.2013.6691675"},{"key":"11_CR19","doi-asserted-by":"publisher","unstructured":"Crane G (2006) What do you do with a million books? D-Lib Magazine 12:3. doi:10.1045\/march2006-crane. ISSN: 1082-9873. http:\/\/www.dlib.org\/dlib\/march06\/crane\/03crane.html","DOI":"10.1045\/march2006-crane"},{"key":"11_CR20","unstructured":"Croft WB, Seo J (2008) Local text reuse detection. In: SIGIR \u201908: Proceedings of the 31st annual international ACM SIGIR conference on Research and development in information retrieval. ACM, New York, pp\u00a0571\u2013578. doi:http:\/\/doi.acm.org\/10.1145\/1390334.1390432. ISBN: 978-1-60558-164-4"},{"key":"11_CR21","doi-asserted-by":"publisher","unstructured":"Croft WB, Bendersky M (2009) Finding text reuse on the web. In: Proceedings of the Second ACM International Conference on Web Search and Data Mining, WSDM \u201909. ACM, New York, pp\u00a0262\u2013271. ISBN: 978-1-60558-390-7. doi:10.1145\/1498759.1498835. http:\/\/doi.acm.org\/10.1145\/1498759.1498835","DOI":"10.1145\/1498759.1498835"},{"key":"11_CR22","doi-asserted-by":"publisher","unstructured":"Elhadad\u00a0N, Barzilay R (2003) Sentence alignment for monolingual comparable corpora. In: Proceedings of the 2003 Conference on Empirical Methods in Natural Language Processing, EMNLP \u201903. Association for Computational Linguistics, Stroudsburg, pp\u00a025\u201332. doi:10.3115\/1119355.1119359. http:\/\/dx.doi.org\/10.3115\/1119355.1119359","DOI":"10.3115\/1119355.1119359"},{"key":"11_CR23","isbn-type":"print","volume-title":"WordNet: an electronic lexical database","year":"1998","unstructured":"Fellbaum C (ed) (1998) WordNet: an electronic lexical database. MIT, Cambridge. ISBN: 978-0-262-06197-1","ISBN":"https:\/\/id.crossref.org\/isbn\/9780262061971"},{"issue":"23","key":"11_CR24","doi-asserted-by":"crossref","first-page":"146","DOI":"10.1080\/00437956.1954.11659520","volume":"10","author":"Z Harris","year":"1954","unstructured":"Harris Z (1954) Distributional structure. Word 10(23):146\u2013162","journal-title":"Word"},{"key":"11_CR25","unstructured":"Hagen M, Beyer A, Busse M, Tippmann M, Rosso P, Stein\u00a0B, Potthast M (2014) Overview of the 6th international competition on plagiarism detection. In: Cappellato L, Ferro L, Halvey M, Kraaij W (eds) Working Notes Papers of the CLEF 2014 Evaluation Labs, CEUR Workshop Proceedings. CLEF and CEUR-WS.org. http:\/\/www.clef-initiative.eu\/publication\/working-notes"},{"key":"11_CR26","unstructured":"Heyer G (2009) Analyse von Bedeutungsver\u00e4nderungen in diachronen Textkorpora. Technical report, Natural Language Processing Group, University of Leipzig, Germany, Februar 2009. Vortrag im Forschungsseminar, Leipzig, Germany"},{"key":"11_CR27","first-page":"289","volume-title":"Kathryn BL","author":"T Hofmann","year":"1999","unstructured":"Hofmann T (1999) Probabilistic latent semantic analysis. In: Kathryn\u00a0BL, Henri P (eds) UAI. Morgan Kaufmann, Stockholm, pp 289\u2013296"},{"key":"11_CR28","unstructured":"Horton R, \u00a0Henderson L (2010) Sequence alignment and similarity in biology and the humanities. J Chicago Colloq Digit Humanit Comput Sci"},{"key":"11_CR29","volume-title":"CS490 final report: investigation of sentence level text reuse algorithms","author":"R Hose","year":"2004","unstructured":"Hose R (2004) CS490 final report: investigation of sentence level text reuse algorithms. At Bits On Our Minds workshop at Cornell University"},{"key":"11_CR30","unstructured":"Hunt E, Stiller\u00a0B, Bocek T (2007) Fast Similarity Search in Large Dictionaries. Technical Report ifi-2007.02, Department of Informatics, University of Zurich. http:\/\/fastss.csg.uzh.ch\/"},{"key":"11_CR31","unstructured":"Klein E, Loper\u00a0E, Bird S (2009) Natural Language Processing with Python. Oreilly Series. O\u2019Reilly Media. ISBN: 9780596516499. http:\/\/books.google.de\/books?id=KGIbfiiP1i4C"},{"key":"11_CR32","unstructured":"Lee J (2007) A computational model of text reuse in ancient literary texts. In: Proceedings of the 45th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Prague, pp\u00a0472\u2013479. http:\/\/www.aclweb.org\/anthology\/P07-1060"},{"key":"11_CR33","unstructured":"Levenshtein VI (1966) Binary codes capable of correcting deletions, insertions, and reversals. Technical Report\u00a08"},{"key":"11_CR34","unstructured":"Mayer T, Cysouw M (2014) Creating a massively parallel bible corpus. In: Calzolari N\u00a0(Conference Chair), Choukri K, Declerck T, Loftsson H, Maegaard B, Mariani J, Moreno A, Odijk J, Piperidis S (eds) Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC\u201914), Reykjavik, Iceland. European Language Resources Association (ELRA). ISBN: 978-2-9517408-8-4"},{"key":"11_CR35","doi-asserted-by":"publisher","unstructured":"Miller GA (1995) WordNet: a lexical database for English. Commun ACM 38(11):39\u201341. doi:10.1145\/219717.219748. ISSN: 0001-0782. http:\/\/doi.acm.org\/10.1145\/219717.219748","DOI":"10.1145\/219717.219748"},{"key":"11_CR36","unstructured":"Mueller M (2006) VosPos: a project for virtual orthographic standardization and part of speech tagging of early modern english texts. http:\/\/panini.northwestern.edu\/mmueller\/nupos.pdf. Accessed 13 Nov 2014"},{"key":"11_CR37","unstructured":"Niekler A, Wiedemann\u00a0G, Heyer G (2014) Brauchen die Digital Humanities eine eigene Methodologie? \u00dcberlegungen zur systematischen Nutzung von Text Mining Verfahren in einem politikwissenschaftlichen Projekt. Proceedings, 03"},{"key":"11_CR38","unstructured":"Nord C, Girona\u00a0J, Talavera L (2000) Dependency-based feature selection for clustering symbolic data. http:\/\/citeseerx.ist.psu.edu\/viewdoc\/summary?doi=10.1.1.29.1720"},{"key":"11_CR39","unstructured":"Potthast M, Beyer A, Busse M, Rangel F, Rosso P, Stamatatos E, Stein\u00a0B, Gollub, T (2013) Recent trends in digital text forensics and its evaluation: plagiarism detection, author identification, and author profiling. In: 4th Int. Conf. of CLEF on information access evaluation meets multilinguality, multimodality, and visualization (CLEF 2013). Springer, New York"},{"key":"11_CR40","isbn-type":"print","volume-title":"Automatic text processing: the transformation, analysis, and retrieval of information by computer","author":"G Salton","year":"1989","unstructured":"Salton G (1989) Automatic text processing: the transformation, analysis, and retrieval of information by computer. Addison-Wesley\/Longman, Boston. ISBN: 0-201-12227-8","ISBN":"https:\/\/id.crossref.org\/isbn\/0201122278"},{"key":"11_CR41","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1002\/j.1538-7305.1948.tb01338.x","volume":"27","author":"CE Shannon","year":"1948","unstructured":"Shannon CE (1948) A mathematical theory of communication. Bell Syst Tech J 27:379\u2013423","journal-title":"Bell Syst Tech J"},{"key":"11_CR42","doi-asserted-by":"publisher","unstructured":"Stein B (2007) Principles of hash-based text retrieval. In: Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval, SIGIR \u201907. ACM, New York, pp\u00a0527\u2013534. doi:10.1145\/1277741.1277832. ISBN: 978-1-59593-597-7. http:\/\/doi.acm.org\/10.1145\/1277741.1277832","DOI":"10.1145\/1277741.1277832"},{"key":"11_CR43","doi-asserted-by":"publisher","unstructured":"Wilkerson DS, Aiken\u00a0A, Schleimer S (2003) Winnowing: local algorithms for document fingerprinting. In: Proceedings of the 2003 ACM SIGMOD international conference on Management of data, SIGMOD \u201903. ACM, New York, pp\u00a076\u201385. doi:10.1145\/872757.872770. ISBN 1-58113-634-X. http:\/\/doi.acm.org\/10.1145\/872757.872770","DOI":"10.1145\/872757.872770"},{"key":"11_CR44","unstructured":"Zesch T, Gurevych\u00a0I, B\u00e4r D (2012) Text reuse detection using a composition of text similarity measures. In: Proceedings of the 24th International Conference on Computational Linguistics (COLING 2012), pp\u00a0167\u2013184"},{"key":"11_CR45","volume-title":"Human behaviour and the principle of least-effort","author":"G Zipf","year":"1949","unstructured":"Zipf G (1949) Human behaviour and the principle of least-effort. Addison-Wesley, Cambridge"}],"container-title":["Theory and Applications of Natural Language Processing","Text Mining"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-12655-5_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,31]],"date-time":"2023-01-31T01:14:20Z","timestamp":1675127660000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-12655-5_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014]]},"ISBN":["9783319126548","9783319126555"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-12655-5_11","relation":{},"ISSN":["2192-032X","2192-0338"],"issn-type":[{"value":"2192-032X","type":"print"},{"value":"2192-0338","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014]]},"assertion":[{"value":"13 December 2014","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}