[ { "key": "4CW4WIT4", "version": 11, "library": { "type": "group", "id": 428432, "name": "Itertextuality and Text Resuse", "links": { "alternate": { "href": "https://www.zotero.org/groups/itertextuality_and_text_resuse", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/428432/items/4CW4WIT4", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/itertextuality_and_text_resuse/items/4CW4WIT4", "type": "text/html" } }, "meta": { "createdByUser": { "id": 716790, "username": "jon.reeve", "name": "Jonathan Reeve", "links": { "alternate": { "href": "https://www.zotero.org/jon.reeve", "type": "text/html" } } }, "creatorSummary": "McKenna and Antonia", "parsedDate": "1994", "numChildren": 0 }, "data": { "key": "4CW4WIT4", "version": 11, "itemType": "journalArticle", "title": "Intertextuality and Joyce’s “Oxen of the Sun” episode in Ulysses: the relation between literary and computational evidence’", "creators": [ { "creatorType": "author", "firstName": "C. W. F.", "lastName": "McKenna" }, { "creatorType": "author", "firstName": "Alexis", "lastName": "Antonia" } ], "abstractNote": "", "publicationTitle": "RISSH", "publisher": "", "place": "", "date": "1994", "volume": "30", "issue": "", "section": "", "partNumber": "", "partTitle": "", "pages": "75–90", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "", "citationKey": "", "url": "http://promethee.philo.ulg.ac.be/RISSHpdf/Annee1994/Articles/WMcKennaetc.pdf", "accessDate": "2017-05-20T15:12:29Z", "PMID": "", "PMCID": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "Intertextuality and Joyce’s “Oxen of the Sun” episode in Ulysses", "language": "", "libraryCatalog": "Google Scholar", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2017-05-20T15:14:58Z", "dateModified": "2017-05-20T15:14:58Z" } }, { "key": "QK537MPA", "version": 9, "library": { "type": "group", "id": 428432, "name": "Itertextuality and Text Resuse", "links": { "alternate": { "href": "https://www.zotero.org/groups/itertextuality_and_text_resuse", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/428432/items/QK537MPA", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/itertextuality_and_text_resuse/items/QK537MPA", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/428432/items/8AHNFMAG", "type": "application/json" } }, "meta": { "createdByUser": { "id": 716790, "username": "jon.reeve", "name": "Jonathan Reeve", "links": { "alternate": { "href": "https://www.zotero.org/jon.reeve", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "QK537MPA", "version": 9, "parentItem": "8AHNFMAG", "itemType": "note", "note": "

Requested from Borrow Direct, 12/29/2016.

", "tags": [], "relations": {}, "dateAdded": "2016-12-29T19:45:10Z", "dateModified": "2016-12-29T19:45:24Z" } }, { "key": "8AHNFMAG", "version": 7, "library": { "type": "group", "id": 428432, "name": "Itertextuality and Text Resuse", "links": { "alternate": { "href": "https://www.zotero.org/groups/itertextuality_and_text_resuse", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/428432/items/8AHNFMAG", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/itertextuality_and_text_resuse/items/8AHNFMAG", "type": "text/html" } }, "meta": { "createdByUser": { "id": 716790, "username": "jon.reeve", "name": "Jonathan Reeve", "links": { "alternate": { "href": "https://www.zotero.org/jon.reeve", "type": "text/html" } } }, "creatorSummary": "Juvan", "parsedDate": "2008", "numChildren": 1 }, "data": { "key": "8AHNFMAG", "version": 7, "itemType": "book", "title": "History and poetics of intertextuality", "creators": [ { "creatorType": "author", "firstName": "Marko", "lastName": "Juvan" } ], "abstractNote": "The poetics of intertextuality proposed in this book, based mainly on semiotics, elucidates factors determining the socio-historically elusive border between general intertextuality and citationality, and explores modes of intertextual representation.", "series": "", "seriesNumber": "", "volume": "", "numberOfVolumes": "", "edition": "", "date": "2008", "publisher": "Purdue University", "place": "West Lafayette, Ind.", "originalDate": "", "originalPublisher": "", "originalPlace": "", "format": "", "numPages": "", "ISBN": "978-1-55753-503-0 1-55753-503-5", "DOI": "", "citationKey": "", "url": "", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "English", "libraryCatalog": "Open WorldCat", "callNumber": "", "rights": "", "extra": "OCLC: 261176641", "tags": [], "collections": [], "relations": {}, "dateAdded": "2016-12-29T19:44:54Z", "dateModified": "2016-12-29T19:44:54Z" } }, { "key": "PU289B7R", "version": 3, "library": { "type": "group", "id": 428432, "name": "Itertextuality and Text Resuse", "links": { "alternate": { "href": "https://www.zotero.org/groups/itertextuality_and_text_resuse", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/428432/items/PU289B7R", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/itertextuality_and_text_resuse/items/PU289B7R", "type": "text/html" } }, "meta": { "createdByUser": { "id": 716790, "username": "jon.reeve", "name": "Jonathan Reeve", "links": { "alternate": { "href": "https://www.zotero.org/jon.reeve", "type": "text/html" } } }, "creatorSummary": "Bär et al.", "numChildren": 2 }, "data": { "key": "PU289B7R", "version": 3, "itemType": "journalArticle", "title": "Text Reuse Detection Using a Composition of Text Similarity Measures", "creators": [ { "creatorType": "author", "firstName": "Daniel", "lastName": "Bär" }, { "creatorType": "author", "firstName": "Torsten", "lastName": "Zesch" }, { "creatorType": "author", "firstName": "Iryna", "lastName": "Gurevych" } ], "abstractNote": "", "publicationTitle": "Proceedings of COLING 2012", "publisher": "", "place": "", "date": "", "volume": "1", "issue": "", "section": "", "partNumber": "", "partTitle": "", "pages": "167-184", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "", "citationKey": "", "url": "https://www.cdc.informatik.tu-darmstadt.de/fileadmin/user_upload/Group_UKP/publikationen/2012/COLING_2012_DaB_published.pdf", "accessDate": "2016-03-13T18:41:48Z", "PMID": "", "PMCID": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2016-03-13T18:41:48Z", "dateModified": "2016-03-13T18:51:57Z" } }, { "key": "ST8II5MK", "version": 4, "library": { "type": "group", "id": 428432, "name": "Itertextuality and Text Resuse", "links": { "alternate": { "href": "https://www.zotero.org/groups/itertextuality_and_text_resuse", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/428432/items/ST8II5MK", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/itertextuality_and_text_resuse/items/ST8II5MK", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/428432/items/PU289B7R", "type": "application/json" } }, "meta": { "createdByUser": { "id": 716790, "username": "jon.reeve", "name": "Jonathan Reeve", "links": { "alternate": { "href": "https://www.zotero.org/jon.reeve", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "ST8II5MK", "version": 4, "parentItem": "PU289B7R", "itemType": "attachment", "linkMode": "imported_url", "title": "Proceedings of COLING 2012 Volume 1 - COLING_2012_DaB_published.pdf", "accessDate": "2016-03-06T22:56:02Z", "url": "https://www.cdc.informatik.tu-darmstadt.de/fileadmin/user_upload/Group_UKP/publikationen/2012/COLING_2012_DaB_published.pdf", "note": "", "contentType": "application/pdf", "charset": "utf-8", "filename": "COLING_2012_DaB_published.pdf", "md5": "022a922d37110985241e7b93794e281a", "mtime": 1457304962000, "tags": [], "relations": {}, "dateAdded": "2016-03-06T22:56:02Z", "dateModified": "2016-03-13T18:41:58Z" } }, { "key": "T5WNG7Z4", "version": 5, "library": { "type": "group", "id": 428432, "name": "Itertextuality and Text Resuse", "links": { "alternate": { "href": "https://www.zotero.org/groups/itertextuality_and_text_resuse", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/428432/items/T5WNG7Z4", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/itertextuality_and_text_resuse/items/T5WNG7Z4", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/428432/items/PU289B7R", "type": "application/json" } }, "meta": { "createdByUser": { "id": 716790, "username": "jon.reeve", "name": "Jonathan Reeve", "links": { "alternate": { "href": "https://www.zotero.org/jon.reeve", "type": "text/html" } } } }, "data": { "key": "T5WNG7Z4", "version": 5, "parentItem": "PU289B7R", "itemType": "attachment", "linkMode": "imported_url", "title": "Proceedings of COLING 2012 Volume 1 - COLING_2012_DaB_published.pdf", "accessDate": "2016-03-13T18:41:49Z", "url": "https://www.cdc.informatik.tu-darmstadt.de/fileadmin/user_upload/Group_UKP/publikationen/2012/COLING_2012_DaB_published.pdf", "note": "", "contentType": "text/html", "charset": "utf-8", "filename": "COLING_2012_DaB_published.html", "md5": "4fb4868c03171d71a2ec28ab8e6e3a7d", "mtime": 1457894509000, "tags": [], "relations": {}, "dateAdded": "2016-03-13T18:41:49Z", "dateModified": "2016-03-13T18:41:49Z" } }, { "key": "6DVA8HWQ", "version": 4, "library": { "type": "group", "id": 428432, "name": "Itertextuality and Text Resuse", "links": { "alternate": { "href": "https://www.zotero.org/groups/itertextuality_and_text_resuse", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/428432/items/6DVA8HWQ", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/itertextuality_and_text_resuse/items/6DVA8HWQ", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/428432/items/WH3HK4E6", "type": "application/json" } }, "meta": { "createdByUser": { "id": 716790, "username": "jon.reeve", "name": "Jonathan Reeve", "links": { "alternate": { "href": "https://www.zotero.org/jon.reeve", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "6DVA8HWQ", "version": 4, "parentItem": "WH3HK4E6", "itemType": "attachment", "linkMode": "imported_url", "title": "[PDF] from aclweb.org", "accessDate": "2016-03-13T17:26:34Z", "url": "http://anthology.aclweb.org/P/P07/P07-1.pdf#page=510", "note": "", "contentType": "application/pdf", "charset": "", "filename": "Lee - 2007 - A computational model of text reuse in ancient lit.pdf", "md5": "5ed9f5cb089391f712344d19284535ac", "mtime": 1457890008000, "tags": [], "relations": {}, "dateAdded": "2016-03-13T17:26:48Z", "dateModified": "2016-03-13T17:26:48Z" } }, { "key": "WH3HK4E6", "version": 3, "library": { "type": "group", "id": 428432, "name": "Itertextuality and Text Resuse", "links": { "alternate": { "href": "https://www.zotero.org/groups/itertextuality_and_text_resuse", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/428432/items/WH3HK4E6", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/itertextuality_and_text_resuse/items/WH3HK4E6", "type": "text/html" } }, "meta": { "createdByUser": { "id": 716790, "username": "jon.reeve", "name": "Jonathan Reeve", "links": { "alternate": { "href": "https://www.zotero.org/jon.reeve", "type": "text/html" } } }, "creatorSummary": "Lee", "parsedDate": "2007", "numChildren": 1 }, "data": { "key": "WH3HK4E6", "version": 3, "itemType": "conferencePaper", "title": "A computational model of text reuse in ancient literary texts", "creators": [ { "creatorType": "author", "firstName": "John", "lastName": "Lee" } ], "abstractNote": "", "proceedingsTitle": "ANNUAL MEETING-ASSOCIATION FOR COMPUTATIONAL LINGUISTICS", "conferenceName": "", "publisher": "", "place": "", "date": "2007", "eventPlace": "", "volume": "45", "issue": "", "numberOfVolumes": "", "pages": "472", "series": "", "seriesNumber": "", "DOI": "", "ISBN": "", "citationKey": "", "url": "http://anthology.aclweb.org/P/P07/P07-1.pdf#page=510", "accessDate": "2016-03-13T17:26:34Z", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "Google Scholar", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2016-03-13T17:26:48Z", "dateModified": "2016-03-13T17:26:48Z" } }, { "key": "AAWII9BD", "version": 4, "library": { "type": "group", "id": 428432, "name": "Itertextuality and Text Resuse", "links": { "alternate": { "href": "https://www.zotero.org/groups/itertextuality_and_text_resuse", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/428432/items/AAWII9BD", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/itertextuality_and_text_resuse/items/AAWII9BD", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/428432/items/9JIQSZEJ", "type": "application/json" } }, "meta": { "createdByUser": { "id": 716790, "username": "jon.reeve", "name": "Jonathan Reeve", "links": { "alternate": { "href": "https://www.zotero.org/jon.reeve", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "AAWII9BD", "version": 4, "parentItem": "9JIQSZEJ", "itemType": "attachment", "linkMode": "imported_url", "title": "[PDF] from herts.ac.uk", "accessDate": "2016-03-12T21:37:42Z", "url": "http://homepages.stca.herts.ac.uk/~comrcml/plagiarism_01.pdf", "note": "", "contentType": "application/pdf", "charset": "", "filename": "Lyon et al. - 2001 - Detecting short passages of similar text in large .pdf", "md5": "2d37b68dfb9bffe525f6613fa3f19daa", "mtime": 1457821033000, "tags": [], "relations": {}, "dateAdded": "2016-03-12T22:17:13Z", "dateModified": "2016-03-12T22:17:13Z" } }, { "key": "9JIQSZEJ", "version": 3, "library": { "type": "group", "id": 428432, "name": "Itertextuality and Text Resuse", "links": { "alternate": { "href": "https://www.zotero.org/groups/itertextuality_and_text_resuse", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/428432/items/9JIQSZEJ", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/itertextuality_and_text_resuse/items/9JIQSZEJ", "type": "text/html" } }, "meta": { "createdByUser": { "id": 716790, "username": "jon.reeve", "name": "Jonathan Reeve", "links": { "alternate": { "href": "https://www.zotero.org/jon.reeve", "type": "text/html" } } }, "creatorSummary": "Lyon et al.", "parsedDate": "2001", "numChildren": 1 }, "data": { "key": "9JIQSZEJ", "version": 3, "itemType": "conferencePaper", "title": "Detecting short passages of similar text in large document collections", "creators": [ { "creatorType": "author", "firstName": "Caroline", "lastName": "Lyon" }, { "creatorType": "author", "firstName": "James", "lastName": "Malcolm" }, { "creatorType": "author", "firstName": "Bob", "lastName": "Dickerson" } ], "abstractNote": "", "proceedingsTitle": "Proceedings of the 2001 Conference on Empirical Methods in Natural Language Processing", "conferenceName": "", "publisher": "", "place": "", "date": "2001", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "118–125", "series": "", "seriesNumber": "", "DOI": "", "ISBN": "", "citationKey": "", "url": "http://homepages.stca.herts.ac.uk/~comrcml/plagiarism_01.pdf", "accessDate": "2016-03-12T21:37:42Z", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "Google Scholar", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2016-03-12T22:17:13Z", "dateModified": "2016-03-12T22:17:13Z" } }, { "key": "JQFNKCJH", "version": 4, "library": { "type": "group", "id": 428432, "name": "Itertextuality and Text Resuse", "links": { "alternate": { "href": "https://www.zotero.org/groups/itertextuality_and_text_resuse", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/428432/items/JQFNKCJH", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/itertextuality_and_text_resuse/items/JQFNKCJH", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/428432/items/WS23KP8G", "type": "application/json" } }, "meta": { "createdByUser": { "id": 716790, "username": "jon.reeve", "name": "Jonathan Reeve", "links": { "alternate": { "href": "https://www.zotero.org/jon.reeve", "type": "text/html" } } } }, "data": { "key": "JQFNKCJH", "version": 4, "parentItem": "WS23KP8G", "itemType": "attachment", "linkMode": "imported_url", "title": "Snapshot", "accessDate": "2016-03-07T16:21:02Z", "url": "http://bommaritollc.com/2014/06/30/advanced-approximate-sentence-matching-python/", "note": "", "contentType": "text/html", "charset": "utf-8", "filename": "advanced-approximate-sentence-matching-python.html", "md5": "92e7a5a96b6062539d370ce1b07e766f", "mtime": 1457367662000, "tags": [], "relations": {}, "dateAdded": "2016-03-07T16:21:02Z", "dateModified": "2016-03-07T16:21:02Z" } }, { "key": "WS23KP8G", "version": 3, "library": { "type": "group", "id": 428432, "name": "Itertextuality and Text Resuse", "links": { "alternate": { "href": "https://www.zotero.org/groups/itertextuality_and_text_resuse", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/428432/items/WS23KP8G", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/itertextuality_and_text_resuse/items/WS23KP8G", "type": "text/html" } }, "meta": { "createdByUser": { "id": 716790, "username": "jon.reeve", "name": "Jonathan Reeve", "links": { "alternate": { "href": "https://www.zotero.org/jon.reeve", "type": "text/html" } } }, "numChildren": 1 }, "data": { "key": "WS23KP8G", "version": 3, "itemType": "blogPost", "title": "Advanced approximate sentence matching in Python | Bommarito Consulting, LLC", "creators": [], "abstractNote": "", "blogTitle": "", "websiteType": "", "date": "", "DOI": "", "citationKey": "", "url": "http://bommaritollc.com/2014/06/30/advanced-approximate-sentence-matching-python/", "accessDate": "2016-03-07T16:21:02Z", "ISSN": "", "shortTitle": "", "language": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2016-03-07T16:21:02Z", "dateModified": "2016-03-07T16:21:02Z" } }, { "key": "CQQEV3R8", "version": 4, "library": { "type": "group", "id": 428432, "name": "Itertextuality and Text Resuse", "links": { "alternate": { "href": "https://www.zotero.org/groups/itertextuality_and_text_resuse", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/428432/items/CQQEV3R8", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/itertextuality_and_text_resuse/items/CQQEV3R8", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/428432/items/8A7AZ2XT", "type": "application/json" } }, "meta": { "createdByUser": { "id": 716790, "username": "jon.reeve", "name": "Jonathan Reeve", "links": { "alternate": { "href": "https://www.zotero.org/jon.reeve", "type": "text/html" } } } }, "data": { "key": "CQQEV3R8", "version": 4, "parentItem": "8A7AZ2XT", "itemType": "attachment", "linkMode": "imported_url", "title": "Snapshot", "accessDate": "2016-03-07T16:21:00Z", "url": "http://bommaritollc.com/2014/06/12/fuzzy-match-sentences-python/", "note": "", "contentType": "text/html", "charset": "utf-8", "filename": "fuzzy-match-sentences-python.html", "md5": "a70a67e8cb98d295c97bd78b561ee965", "mtime": 1457367660000, "tags": [], "relations": {}, "dateAdded": "2016-03-07T16:21:00Z", "dateModified": "2016-03-07T16:21:00Z" } }, { "key": "MAHK4PZF", "version": 4, "library": { "type": "group", "id": 428432, "name": "Itertextuality and Text Resuse", "links": { "alternate": { "href": "https://www.zotero.org/groups/itertextuality_and_text_resuse", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/428432/items/MAHK4PZF", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/itertextuality_and_text_resuse/items/MAHK4PZF", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/428432/items/FCPQQN88", "type": "application/json" } }, "meta": { "createdByUser": { "id": 716790, "username": "jon.reeve", "name": "Jonathan Reeve", "links": { "alternate": { "href": "https://www.zotero.org/jon.reeve", "type": "text/html" } } } }, "data": { "key": "MAHK4PZF", "version": 4, "parentItem": "FCPQQN88", "itemType": "attachment", "linkMode": "imported_url", "title": "Snapshot", "accessDate": "2016-03-07T16:20:55Z", "url": "http://bommaritollc.com/2014/06/12/fuzzy-match-sentences-python/", "note": "", "contentType": "text/html", "charset": "utf-8", "filename": "fuzzy-match-sentences-python.html", "md5": "b298218e8e343101037ac28510f935e7", "mtime": 1457367655000, "tags": [], "relations": {}, "dateAdded": "2016-03-07T16:20:55Z", "dateModified": "2016-03-07T16:20:55Z" } }, { "key": "FCPQQN88", "version": 3, "library": { "type": "group", "id": 428432, "name": "Itertextuality and Text Resuse", "links": { "alternate": { "href": "https://www.zotero.org/groups/itertextuality_and_text_resuse", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/428432/items/FCPQQN88", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/itertextuality_and_text_resuse/items/FCPQQN88", "type": "text/html" } }, "meta": { "createdByUser": { "id": 716790, "username": "jon.reeve", "name": "Jonathan Reeve", "links": { "alternate": { "href": "https://www.zotero.org/jon.reeve", "type": "text/html" } } }, "creatorSummary": "Bommarito", "numChildren": 1 }, "data": { "key": "FCPQQN88", "version": 3, "itemType": "blogPost", "title": "Fuzzy match sentences in Python | Bommarito Consulting, LLC", "creators": [ { "creatorType": "author", "firstName": "Author: Michael", "lastName": "Bommarito" } ], "abstractNote": "", "blogTitle": "", "websiteType": "", "date": "", "DOI": "", "citationKey": "", "url": "http://bommaritollc.com/2014/06/12/fuzzy-match-sentences-python/", "accessDate": "2016-03-07T16:20:55Z", "ISSN": "", "shortTitle": "", "language": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2016-03-07T16:20:55Z", "dateModified": "2016-03-07T16:20:55Z" } }, { "key": "MDSJBAB8", "version": 4, "library": { "type": "group", "id": 428432, "name": "Itertextuality and Text Resuse", "links": { "alternate": { "href": "https://www.zotero.org/groups/itertextuality_and_text_resuse", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/428432/items/MDSJBAB8", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/itertextuality_and_text_resuse/items/MDSJBAB8", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/428432/items/8EXIWE52", "type": "application/json" } }, "meta": { "createdByUser": { "id": 716790, "username": "jon.reeve", "name": "Jonathan Reeve", "links": { "alternate": { "href": "https://www.zotero.org/jon.reeve", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "MDSJBAB8", "version": 4, "parentItem": "8EXIWE52", "itemType": "attachment", "linkMode": "imported_url", "title": "[PDF] from aclweb.org", "accessDate": "2016-03-07T16:17:38Z", "url": "http://anthology.aclweb.org/P/P07/P07-1.pdf#page=510", "note": "", "contentType": "application/pdf", "charset": "", "filename": "Lee - 2007 - A computational model of text reuse in ancient lit.pdf", "md5": "5ed9f5cb089391f712344d19284535ac", "mtime": 1457367521000, "tags": [], "relations": {}, "dateAdded": "2016-03-07T16:17:38Z", "dateModified": "2016-03-07T16:18:41Z" } }, { "key": "8EXIWE52", "version": 3, "library": { "type": "group", "id": 428432, "name": "Itertextuality and Text Resuse", "links": { "alternate": { "href": "https://www.zotero.org/groups/itertextuality_and_text_resuse", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/428432/items/8EXIWE52", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/itertextuality_and_text_resuse/items/8EXIWE52", "type": "text/html" } }, "meta": { "createdByUser": { "id": 716790, "username": "jon.reeve", "name": "Jonathan Reeve", "links": { "alternate": { "href": "https://www.zotero.org/jon.reeve", "type": "text/html" } } }, "creatorSummary": "Lee", "parsedDate": "2007", "numChildren": 1 }, "data": { "key": "8EXIWE52", "version": 3, "itemType": "conferencePaper", "title": "A computational model of text reuse in ancient literary texts", "creators": [ { "creatorType": "author", "firstName": "John", "lastName": "Lee" } ], "abstractNote": "", "proceedingsTitle": "ANNUAL MEETING-ASSOCIATION FOR COMPUTATIONAL LINGUISTICS", "conferenceName": "", "publisher": "", "place": "", "date": "2007", "eventPlace": "", "volume": "45", "issue": "", "numberOfVolumes": "", "pages": "472", "series": "", "seriesNumber": "", "DOI": "", "ISBN": "", "citationKey": "", "url": "http://anthology.aclweb.org/P/P07/P07-1.pdf#page=510", "accessDate": "2016-03-07T16:17:38Z", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "Google Scholar", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2016-03-07T16:17:38Z", "dateModified": "2016-03-07T16:17:38Z" } }, { "key": "K2XM4ECQ", "version": 4, "library": { "type": "group", "id": 428432, "name": "Itertextuality and Text Resuse", "links": { "alternate": { "href": "https://www.zotero.org/groups/itertextuality_and_text_resuse", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/428432/items/K2XM4ECQ", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/itertextuality_and_text_resuse/items/K2XM4ECQ", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/428432/items/J28J6UIM", "type": "application/json" } }, "meta": { "createdByUser": { "id": 716790, "username": "jon.reeve", "name": "Jonathan Reeve", "links": { "alternate": { "href": "https://www.zotero.org/jon.reeve", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "K2XM4ECQ", "version": 4, "parentItem": "J28J6UIM", "itemType": "attachment", "linkMode": "imported_url", "title": "[PDF] from psu.edu", "accessDate": "2016-03-07T16:15:06Z", "url": "http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.458.9440&rep=rep1&type=pdf", "note": "", "contentType": "application/pdf", "charset": "", "filename": "Chong et al. - 2010 - Using natural language processing for automatic de.pdf", "md5": "89c4e20dac0beb9c948fb894812d4a6f", "mtime": 1457367307000, "tags": [], "relations": {}, "dateAdded": "2016-03-07T16:15:06Z", "dateModified": "2016-03-07T16:15:07Z" } }, { "key": "J28J6UIM", "version": 3, "library": { "type": "group", "id": 428432, "name": "Itertextuality and Text Resuse", "links": { "alternate": { "href": "https://www.zotero.org/groups/itertextuality_and_text_resuse", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/428432/items/J28J6UIM", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/itertextuality_and_text_resuse/items/J28J6UIM", "type": "text/html" } }, "meta": { "createdByUser": { "id": 716790, "username": "jon.reeve", "name": "Jonathan Reeve", "links": { "alternate": { "href": "https://www.zotero.org/jon.reeve", "type": "text/html" } } }, "creatorSummary": "Chong et al.", "parsedDate": "2010", "numChildren": 1 }, "data": { "key": "J28J6UIM", "version": 3, "itemType": "conferencePaper", "title": "Using natural language processing for automatic detection of plagiarism", "creators": [ { "creatorType": "author", "firstName": "Miranda", "lastName": "Chong" }, { "creatorType": "author", "firstName": "Lucia", "lastName": "Specia" }, { "creatorType": "author", "firstName": "Ruslan", "lastName": "Mitkov" } ], "abstractNote": "", "proceedingsTitle": "Proceedings of the 4th International Plagiarism Conference (IPC 2010), Newcastle, UK", "conferenceName": "", "publisher": "Citeseer", "place": "", "date": "2010", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "", "series": "", "seriesNumber": "", "DOI": "", "ISBN": "", "citationKey": "", "url": "http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.458.9440&rep=rep1&type=pdf", "accessDate": "2016-03-07T16:15:06Z", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "Google Scholar", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2016-03-07T16:15:06Z", "dateModified": "2016-03-07T16:15:06Z" } }, { "key": "9NK8V5W5", "version": 4, "library": { "type": "group", "id": 428432, "name": "Itertextuality and Text Resuse", "links": { "alternate": { "href": "https://www.zotero.org/groups/itertextuality_and_text_resuse", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/428432/items/9NK8V5W5", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/itertextuality_and_text_resuse/items/9NK8V5W5", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/428432/items/BD3247X4", "type": "application/json" } }, "meta": { "createdByUser": { "id": 716790, "username": "jon.reeve", "name": "Jonathan Reeve", "links": { "alternate": { "href": "https://www.zotero.org/jon.reeve", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "9NK8V5W5", "version": 4, "parentItem": "BD3247X4", "itemType": "attachment", "linkMode": "imported_url", "title": "ACM Full Text PDF", "accessDate": "2016-03-06T22:51:52Z", "url": "http://dl.acm.org.ezproxy.cul.columbia.edu/ft_gateway.cfm?id=1390432&type=pdf", "note": "", "contentType": "application/pdf", "charset": "", "filename": "Seo and Croft - 2008 - Local Text Reuse Detection.pdf", "md5": "8f9e8b1a5be3c95fa0f89ba38494e337", "mtime": 1457304712000, "tags": [], "relations": {}, "dateAdded": "2016-03-06T22:51:52Z", "dateModified": "2016-03-06T22:51:53Z" } }, { "key": "BD3247X4", "version": 3, "library": { "type": "group", "id": 428432, "name": "Itertextuality and Text Resuse", "links": { "alternate": { "href": "https://www.zotero.org/groups/itertextuality_and_text_resuse", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/428432/items/BD3247X4", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/itertextuality_and_text_resuse/items/BD3247X4", "type": "text/html" } }, "meta": { "createdByUser": { "id": 716790, "username": "jon.reeve", "name": "Jonathan Reeve", "links": { "alternate": { "href": "https://www.zotero.org/jon.reeve", "type": "text/html" } } }, "creatorSummary": "Seo and Croft", "parsedDate": "2008", "numChildren": 1 }, "data": { "key": "BD3247X4", "version": 3, "itemType": "conferencePaper", "title": "Local Text Reuse Detection", "creators": [ { "creatorType": "author", "firstName": "Jangwon", "lastName": "Seo" }, { "creatorType": "author", "firstName": "W. Bruce", "lastName": "Croft" } ], "abstractNote": "Text reuse occurs in many different types of documents and for many different reasons. One form of reuse, duplicate or near-duplicate documents, has been a focus of researchers because of its importance in Web search. Local text reuse occurs when sentences, facts or passages, rather than whole documents, are reused and modified. Detecting this type of reuse can be the basis of new tools for text analysis. In this paper, we introduce a new approach to detecting local text reuse and compare it to other approaches. This comparison involves a study of the amount and type of reuse that occurs in real documents, including TREC newswire and blog collections.", "proceedingsTitle": "Proceedings of the 31st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval", "conferenceName": "", "publisher": "ACM", "place": "New York, NY, USA", "date": "2008", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "571–578", "series": "SIGIR '08", "seriesNumber": "", "DOI": "10.1145/1390334.1390432", "ISBN": "978-1-60558-164-4", "citationKey": "", "url": "http://doi.acm.org/10.1145/1390334.1390432", "accessDate": "2016-03-06T22:51:52Z", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "ACM Digital Library", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "fingerprinting", "type": 1 }, { "tag": "information flow", "type": 1 }, { "tag": "text reuse", "type": 1 } ], "collections": [], "relations": {}, "dateAdded": "2016-03-06T22:51:52Z", "dateModified": "2016-03-06T22:51:52Z" } }, { "key": "BWK3N4Z4", "version": 4, "library": { "type": "group", "id": 428432, "name": "Itertextuality and Text Resuse", "links": { "alternate": { "href": "https://www.zotero.org/groups/itertextuality_and_text_resuse", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/428432/items/BWK3N4Z4", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/itertextuality_and_text_resuse/items/BWK3N4Z4", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/428432/items/3CZKPVXD", "type": "application/json" } }, "meta": { "createdByUser": { "id": 716790, "username": "jon.reeve", "name": "Jonathan Reeve", "links": { "alternate": { "href": "https://www.zotero.org/jon.reeve", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "BWK3N4Z4", "version": 4, "parentItem": "3CZKPVXD", "itemType": "attachment", "linkMode": "imported_url", "title": "ACM Full Text PDF", "accessDate": "2016-03-06T22:49:31Z", "url": "http://dl.acm.org.ezproxy.cul.columbia.edu/ft_gateway.cfm?id=1835687&type=pdf", "note": "", "contentType": "application/pdf", "charset": "", "filename": "Barrón-Cedeño - 2010 - On the Mono- and Cross-language Detection of Text .pdf", "md5": "6e6e146ebb7c2f5184a90504305afa77", "mtime": 1457304572000, "tags": [], "relations": {}, "dateAdded": "2016-03-06T22:49:31Z", "dateModified": "2016-03-06T22:49:32Z" } }, { "key": "3CZKPVXD", "version": 3, "library": { "type": "group", "id": 428432, "name": "Itertextuality and Text Resuse", "links": { "alternate": { "href": "https://www.zotero.org/groups/itertextuality_and_text_resuse", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/428432/items/3CZKPVXD", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/itertextuality_and_text_resuse/items/3CZKPVXD", "type": "text/html" } }, "meta": { "createdByUser": { "id": 716790, "username": "jon.reeve", "name": "Jonathan Reeve", "links": { "alternate": { "href": "https://www.zotero.org/jon.reeve", "type": "text/html" } } }, "creatorSummary": "Barrón-Cedeño", "parsedDate": "2010", "numChildren": 1 }, "data": { "key": "3CZKPVXD", "version": 3, "itemType": "conferencePaper", "title": "On the Mono- and Cross-language Detection of Text Reuse and Plagiarism", "creators": [ { "creatorType": "author", "firstName": "Alberto", "lastName": "Barrón-Cedeño" } ], "abstractNote": "Plagiarism, the unacknowledged reuse of text, has increased in recent years due to the large amount of texts readily available. For instance, recent studies claim that nowadays a high rate of student reports include plagiarism, making manual plagiarism detection practically infeasible. Automatic plagiarism detection tools assist experts to analyse documents for plagiarism. Nevertheless, the lack of standard collections with cases of plagiarism has prevented accurate comparing models, making differences hard to appreciate. Seminal efforts on the detection of text reuse [2] have fostered the composition of standard resources for the accurate evaluation and comparison of methods. The aim of this PhD thesis is to address three of the main problems in the development of better models for automatic plagiarism detection: (i) the adequate identification of good potential sources for a given suspicious text; (ii) the detection of plagiarism despite modifications, such as words substitution and paraphrasing (special stress is given to cross-language plagiarism); and (iii) the generation of standard collections of cases of plagiarism and text reuse in order to provide a framework for accurate comparison of models. Regarding difficulties (i) and (ii) , we have carried out preliminary experiments over the METER corpus [2]. Given a suspicious document dq and a collection of potential source documents D, the process is divided in two steps. First, a small subset of potential source documents D* in D is retrieved. The documents d in D* are the most related to dq and, therefore, the most likely to include the source of the plagiarised fragments in it. We performed this stage on the basis of the Kullback-Leibler distance, over a subsample of document's vocabularies. Afterwards, a detailed analysis is carried out comparing dq to every d in D* in order to identify potential cases of plagiarism and their source. This comparison was made on the basis of word n-grams, by considering n = {2, 3}. These n-gram levels are flexible enough to properly retrieve plagiarised fragments and their sources despite modifications [1]. The result is offered to the user to take the final decision. Further experiments were done in both stages in order to compare other similarity measures, such as the cosine measure, the Jaccard coefficient and diverse fingerprinting and probabilistic models. One of the main weaknesses of currently available models is that they are unable to detect cross-language plagiarism. Approaching the detection of this kind of plagiarism is of high relevance, as the most of the information published is written in English, and authors in other languages may find it attractive to make use of direct translations. Our experiments, carried out over parallel and a comparable corpora, show that models of \"standard\" cross-language information retrieval are not enough. In fact, if the analysed source and target languages are related in some way (common linguistic ancestors or technical vocabulary), a simple comparison based on character n-grams seems to be the option. However, in those cases where the relation between the implied languages is weaker, other models, such as those based on statistical machine translation, are necessary [3]. We plan to perform further experiments, mainly to approach the detection of cross-language plagiarism. In order to do that, we will use the corpora developed under the framework of the PAN competition on plagiarism detection (cf. PAN@CLEF: http://pan.webis.de). Models that consider cross-language thesauri and comparison of cognates will also be applied.", "proceedingsTitle": "Proceedings of the 33rd International ACM SIGIR Conference on Research and Development in Information Retrieval", "conferenceName": "", "publisher": "ACM", "place": "New York, NY, USA", "date": "2010", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "914–914", "series": "SIGIR '10", "seriesNumber": "", "DOI": "10.1145/1835449.1835687", "ISBN": "978-1-4503-0153-4", "citationKey": "", "url": "http://doi.acm.org/10.1145/1835449.1835687", "accessDate": "2016-03-06T22:49:31Z", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "ACM Digital Library", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "cross-language plagiarism detection", "type": 1 }, { "tag": "plagiarism detection", "type": 1 }, { "tag": "text similarity", "type": 1 } ], "collections": [], "relations": {}, "dateAdded": "2016-03-06T22:49:31Z", "dateModified": "2016-03-06T22:49:31Z" } }, { "key": "C6F3Q9Z4", "version": 4, "library": { "type": "group", "id": 428432, "name": "Itertextuality and Text Resuse", "links": { "alternate": { "href": "https://www.zotero.org/groups/itertextuality_and_text_resuse", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/428432/items/C6F3Q9Z4", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/itertextuality_and_text_resuse/items/C6F3Q9Z4", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/428432/items/82RRVQ47", "type": "application/json" } }, "meta": { "createdByUser": { "id": 716790, "username": "jon.reeve", "name": "Jonathan Reeve", "links": { "alternate": { "href": "https://www.zotero.org/jon.reeve", "type": "text/html" } } }, "numChildren": 0 }, "data": { "key": "C6F3Q9Z4", "version": 4, "parentItem": "82RRVQ47", "itemType": "attachment", "linkMode": "imported_url", "title": "ACM Full Text PDF", "accessDate": "2016-03-05T22:24:13Z", "url": "http://dl.acm.org/ft_gateway.cfm?id=1073110&type=pdf", "note": "", "contentType": "application/pdf", "charset": "", "filename": "Clough et al. - 2002 - METER MEasuring TExt Reuse.pdf", "md5": "3e4d133d6df745c8a760670e2cf5df94", "mtime": 1457216653000, "tags": [], "relations": {}, "dateAdded": "2016-03-05T22:24:13Z", "dateModified": "2016-03-05T22:24:14Z" } }, { "key": "82RRVQ47", "version": 3, "library": { "type": "group", "id": 428432, "name": "Itertextuality and Text Resuse", "links": { "alternate": { "href": "https://www.zotero.org/groups/itertextuality_and_text_resuse", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/428432/items/82RRVQ47", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/itertextuality_and_text_resuse/items/82RRVQ47", "type": "text/html" } }, "meta": { "createdByUser": { "id": 716790, "username": "jon.reeve", "name": "Jonathan Reeve", "links": { "alternate": { "href": "https://www.zotero.org/jon.reeve", "type": "text/html" } } }, "creatorSummary": "Clough et al.", "parsedDate": "2002", "numChildren": 1 }, "data": { "key": "82RRVQ47", "version": 3, "itemType": "conferencePaper", "title": "METER: MEasuring TExt Reuse", "creators": [ { "creatorType": "author", "firstName": "Paul", "lastName": "Clough" }, { "creatorType": "author", "firstName": "Robert", "lastName": "Gaizauskas" }, { "creatorType": "author", "firstName": "Scott S. L.", "lastName": "Piao" }, { "creatorType": "author", "firstName": "Yorick", "lastName": "Wilks" } ], "abstractNote": "In this paper we present results from the METER (MEasuring TExt Reuse) project whose aim is to explore issues pertaining to text reuse and derivation, especially in the context of newspapers using newswire sources. Although the reuse of text by journalists has been studied in linguistics, we are not aware of any investigation using existing computational methods for this particular task. We investigate the classification of newspaper articles according to their degree of dependence upon, or derivation from, a newswire source using a simple 3-level scheme designed by journalists. Three approaches to measuring text similarity are considered: n-gram overlap, Greedy String Tiling, and sentence alignment. Measured against a manually annotated corpus of source and derived news text, we show that a combined classifier with features automatically selected performs best overall for the ternary classification achieving an average F1-measure score of 0.664 across all three categories.", "proceedingsTitle": "Proceedings of the 40th Annual Meeting on Association for Computational Linguistics", "conferenceName": "", "publisher": "Association for Computational Linguistics", "place": "Stroudsburg, PA, USA", "date": "2002", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "152–159", "series": "ACL '02", "seriesNumber": "", "DOI": "10.3115/1073083.1073110", "ISBN": "", "citationKey": "", "url": "http://dx.doi.org/10.3115/1073083.1073110", "accessDate": "2016-03-05T22:24:13Z", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "METER", "language": "", "libraryCatalog": "ACM Digital Library", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2016-03-05T22:24:13Z", "dateModified": "2016-03-05T22:24:13Z" } } ]