{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T02:05:29Z","timestamp":1781661929657,"version":"3.54.5"},"reference-count":34,"publisher":"Oxford University Press (OUP)","issue":"1","content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["J Am Med Inform Assoc"],"published-print":{"date-parts":[[2014,1]]},"DOI":"10.1136\/amiajnl-2012-001552","type":"journal-article","created":{"date-parts":[[2013,5,29]],"date-time":"2013-05-29T07:05:46Z","timestamp":1369811146000},"page":"105-110","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":6,"title":["Comparing Medline citations using modified N-grams: Table 1"],"prefix":"10.1093","volume":"21","author":[{"given":"Rao Muhammad Adeel","family":"Nawab","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mark","family":"Stevenson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paul","family":"Clough","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2014,1,1]]},"reference":[{"key":"2015062501455431000_21.1.105.1","unstructured":"Broder A . On the resemblance and containment of documents. Proceedings of the Conference on Compression and Complexity of Sequences; 1997, IEEE Computer Society, 21\u20139."},{"key":"2015062501455431000_21.1.105.2","doi-asserted-by":"publisher","DOI":"10.1002\/asi.10170"},{"key":"2015062501455431000_21.1.105.3","doi-asserted-by":"crossref","unstructured":"Kim J Candan KS Tatemura J . Efficient overlap and content reuse detection in blogs and online news articles. In: Proceedings of the 18th International Conference on World Wide Web WWW-09; 2009, ACM, 81\u201390.","DOI":"10.1145\/1526709.1526721"},{"key":"2015062501455431000_21.1.105.4","doi-asserted-by":"publisher","DOI":"10.1302\/0301-620X.86B5.14725"},{"key":"2015062501455431000_21.1.105.5","doi-asserted-by":"publisher","DOI":"10.1067\/mhn.2002.122698"},{"key":"2015062501455431000_21.1.105.6","doi-asserted-by":"publisher","DOI":"10.1016\/j.bjps.2005.11.039"},{"key":"2015062501455431000_21.1.105.7","unstructured":"Clough P Gaizauskas R Piao S . Measuring text reuse. Proceedings of the 40th Annual Meeting of the Association of Computational Linguistics; 2002:152\u20139."},{"key":"2015062501455431000_21.1.105.8","unstructured":"Nawab R Stevenson M Clough P . Detecting text reuse with modified and weighted n-grams. *SEM 2012:The First Joint Conference on Lexical and Computational Semantics\u2014Volume 1: Proceedings of the main conference and the shared task; 2012:54\u20138."},{"key":"2015062501455431000_21.1.105.9","unstructured":"Lyon C Malcolm J Dickerson B . Detecting short passages of similar text in large document collections. Proceedings of the Conference on Empirical Methods in Natural Language Processing; 2001:118\u201325."},{"key":"2015062501455431000_21.1.105.10","unstructured":"Stein B Rosso P Stamatatos E . 3rd PAN workshop on uncovering plagiarism, authorship and social software misuse. 25th Annual Conference of the Spanish Society for Natural Language Processing (SEPLN); 2009:1\u201377."},{"key":"2015062501455431000_21.1.105.11","unstructured":"Potthast M Stein B Eiselt A . Overview of the 2nd International Competition on Plagiarism Detection. Proceedings of the CLEF10 Workshop on Uncovering Plagiarism, Authorship and Social Software Misuse; 2010."},{"key":"2015062501455431000_21.1.105.12","unstructured":"Potthast M Eiselt A Barr\u00f3n-Cede\u00f1o A . Overview of the 3rd International Competition on Plagiarism Detection. Notebook Papers of CLEF 11 Labs and Workshops; 2011."},{"key":"2015062501455431000_21.1.105.13","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btm574"},{"key":"2015062501455431000_21.1.105.14","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btl388"},{"key":"2015062501455431000_21.1.105.15","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btq146"},{"key":"2015062501455431000_21.1.105.16","unstructured":"Manning H Sch\u00fctze H . Foundations of statistical natural language processing. MIT Press: Cambridge, 1999."},{"key":"2015062501455431000_21.1.105.17","doi-asserted-by":"crossref","unstructured":"Cover T Thomas J . Elements of information theory. New York: Wiley, 1991.","DOI":"10.1002\/0471200611"},{"key":"2015062501455431000_21.1.105.18","unstructured":"Chen C Yeh J Ke H . Plagiarism Detection using ROUGE and WordNet. In J Comput 2010;2:34\u201344."},{"key":"2015062501455431000_21.1.105.19","unstructured":"Chong M Specia L . Lexical generalisation for word-level matching in plagiarism detection. Proceedings of the recent advances in natural language processing (RANLP); 2011:704\u20139."},{"key":"2015062501455431000_21.1.105.20","doi-asserted-by":"crossref","unstructured":"Stein B Eissen SM Potthast M . Strategies for retrieving plagiarized documents. Proceedings of the 30th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval; 2007:825\u20136.","DOI":"10.1145\/1277741.1277928"},{"key":"2015062501455431000_21.1.105.21","doi-asserted-by":"crossref","unstructured":"Barron-Cede\u00f1o A Rosso P Benedi J . Reducing the plagiarism detection search space on the basis of the Kullback-Leibler distance. Proceedings of 10th International Conference on Computational Linguistics and Intelligent Text Processing; 2009, Springer, 523\u201334.","DOI":"10.1007\/978-3-642-00382-0_42"},{"key":"2015062501455431000_21.1.105.22","doi-asserted-by":"crossref","unstructured":"Nawab RMA Stevenson M Clough P . Retrieving candidate plagiarised documents using query expansion. Proceedings of the 34th European Conference on Information Retrieval (ECIR); 2012, Springer, 207\u201318.","DOI":"10.1007\/978-3-642-28997-2_18"},{"key":"2015062501455431000_21.1.105.23","unstructured":"Potthast M Gollub T Hagen M . Overview of the 4th International Competition on Plagiarism Detection. CLEF 2012 Evaluation Labs and Workshop\u2014Working Notes Papers, 2012."},{"key":"2015062501455431000_21.1.105.24","unstructured":"Nawab RMA . Mono-lingual paraphrased text reuse and plagiarism detection. [PhD thesis] Department of Computer Science, University of Sheffield, 2012."},{"key":"2015062501455431000_21.1.105.25","unstructured":"Chong M Specia L Mitkov R . Using natural language processing for automatic detection of plagiarism. Proceedings of the 4th International Plagiarism Conference (IPC-2010), 2010."},{"key":"2015062501455431000_21.1.105.26","unstructured":"Witten L Frank E Hall M . Data mining: practical machine learning tools and techniques. Morgan Kaufmann, 2011."},{"key":"2015062501455431000_21.1.105.27","doi-asserted-by":"publisher","DOI":"10.1136\/jamia.2009.002733"},{"key":"2015062501455431000_21.1.105.28","unstructured":"Ceska Z . Automatic plagiarism detection based on latent semantic analysis. [PhD thesis] Czech Republic, University of West Bohemia, 2009."},{"key":"2015062501455431000_21.1.105.29","unstructured":"Nelson S Powell T Humphreys B . The Unified Medical Language System (UMLS) project. In: Kent A Hall CM Encyclopedia of library and information science. Marcel Dekker, 2002:369."},{"key":"2015062501455431000_21.1.105.30","doi-asserted-by":"crossref","unstructured":"Papineni K Roukos S Ward T . BLEU: a method for automatic evaluation of machine translation. Proceedings of 40th Annual Meeting of the Association of Computational Linguistics; 2002:311\u20138.","DOI":"10.3115\/1073083.1073135"},{"key":"2015062501455431000_21.1.105.31","unstructured":"Lin CY . ROUGE: a package for automatic evaluation of summaries. Proceedings of Workshop on Text Summarization, Post-Conference Workshop of ACL; 2004:74\u201381."},{"key":"2015062501455431000_21.1.105.32","doi-asserted-by":"crossref","unstructured":"Stolcke A . SRILM: an extensible language modeling toolkit. Proceedings of the International Conference on Spoken Language Processing; 2002:901\u20134.","DOI":"10.21437\/ICSLP.2002-303"},{"key":"2015062501455431000_21.1.105.33","doi-asserted-by":"crossref","unstructured":"Wang W Stolcke A Zheng J . Reranking machine translation hypotheses with structured and web-based language models. IEEE Workshop on Automatic Speech Recognition & Understanding; 2007, IEEE, 159\u201364.","DOI":"10.1109\/ASRU.2007.4430102"},{"key":"2015062501455431000_21.1.105.34","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkm221"}],"container-title":["Journal of the American Medical Informatics Association"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/jamia\/article-pdf\/21\/1\/105\/6035547\/21-1-105.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T23:58:42Z","timestamp":1688255922000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamia\/article-lookup\/doi\/10.1136\/amiajnl-2012-001552"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,1]]},"references-count":34,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2014,1,1]]},"published-print":{"date-parts":[[2014,1]]}},"alternative-id":["10.1136\/amiajnl-2012-001552"],"URL":"https:\/\/doi.org\/10.1136\/amiajnl-2012-001552","relation":{},"ISSN":["1067-5027","1527-974X"],"issn-type":[{"value":"1067-5027","type":"print"},{"value":"1527-974X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,1]]}}}