{"id":"https://openalex.org/W3209033320","doi":"https://doi.org/10.5281/zenodo.3608000","title":"Identifying Machine-Paraphrased Plagiarism","display_name":"Identifying Machine-Paraphrased Plagiarism","publication_year":2021,"publication_date":"2021-01-14","ids":{"openalex":"https://openalex.org/W3209033320","doi":"https://doi.org/10.5281/zenodo.3608000","mag":"3209033320"},"language":"en","primary_location":{"id":"pmh:oai:figshare.com:article/11673411","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Dataset"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Wahle, Jan Philip","orcid":null},"institutions":[{"id":"https://openalex.org/I74656192","display_name":"University of G\u00f6ttingen","ror":"https://ror.org/01y9bpm73","country_code":"DE","type":"education","lineage":["https://openalex.org/I74656192"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Wahle, Jan Philip","raw_affiliation_strings":["University of G\u00f6ttingen"],"affiliations":[{"raw_affiliation_string":"University of G\u00f6ttingen","institution_ids":["https://openalex.org/I74656192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081763922","display_name":"Terry Ruas","orcid":"https://orcid.org/0000-0002-9440-780X"},"institutions":[{"id":"https://openalex.org/I74656192","display_name":"University of G\u00f6ttingen","ror":"https://ror.org/01y9bpm73","country_code":"DE","type":"education","lineage":["https://openalex.org/I74656192"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ruas, Terry","raw_affiliation_strings":["University of G\u00f6ttingen"],"affiliations":[{"raw_affiliation_string":"University of G\u00f6ttingen","institution_ids":["https://openalex.org/I74656192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048058395","display_name":"Tom\u00e1\u0161 Folt\u00fdnek","orcid":"https://orcid.org/0000-0001-8412-5553"},"institutions":[{"id":"https://openalex.org/I56081889","display_name":"Mendel University in Brno","ror":"https://ror.org/058aeep47","country_code":"CZ","type":"education","lineage":["https://openalex.org/I56081889"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Foltynek, Tomas","raw_affiliation_strings":["Mendel University in Brno"],"affiliations":[{"raw_affiliation_string":"Mendel University in Brno","institution_ids":["https://openalex.org/I56081889"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060549879","display_name":"Norman Meuschke","orcid":null},"institutions":[{"id":"https://openalex.org/I74656192","display_name":"University of G\u00f6ttingen","ror":"https://ror.org/01y9bpm73","country_code":"DE","type":"education","lineage":["https://openalex.org/I74656192"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Meuschke, Norman","raw_affiliation_strings":["University of G\u00f6ttingen"],"affiliations":[{"raw_affiliation_string":"University of G\u00f6ttingen","institution_ids":["https://openalex.org/I74656192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058837356","display_name":"B\u00e9la Gipp","orcid":"https://orcid.org/0000-0001-6522-3019"},"institutions":[{"id":"https://openalex.org/I74656192","display_name":"University of G\u00f6ttingen","ror":"https://ror.org/01y9bpm73","country_code":"DE","type":"education","lineage":["https://openalex.org/I74656192"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Gipp, Bela","raw_affiliation_strings":["University of G\u00f6ttingen"],"affiliations":[{"raw_affiliation_string":"University of G\u00f6ttingen","institution_ids":["https://openalex.org/I74656192"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74656192"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11492","display_name":"Academic integrity and plagiarism","score":0.9611999988555908,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11492","display_name":"Academic integrity and plagiarism","score":0.9611999988555908,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5555070638656616},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.45122426748275757},{"id":"https://openalex.org/keywords/mathematics-education","display_name":"Mathematics education","score":0.4278483986854553},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3963814377784729},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3927857279777527},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3482220768928528},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19358977675437927},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.13584643602371216}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5555070638656616},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.45122426748275757},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.4278483986854553},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3963814377784729},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3927857279777527},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3482220768928528},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19358977675437927},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.13584643602371216}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:figshare.com:article/11673411","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Dataset"},{"id":"pmh:oai:zenodo.org:3608000","is_oa":true,"landing_page_url":"https://zenodo.org/record/3608000","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/other"},{"id":"doi:10.5281/zenodo.3608000","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.3608000","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"dataset"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/11673411","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Dataset"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4231937131","https://openalex.org/W3188962172","https://openalex.org/W323219885","https://openalex.org/W2063928587","https://openalex.org/W2772917594","https://openalex.org/W4292559016","https://openalex.org/W1487966966","https://openalex.org/W1589342014","https://openalex.org/W4306742369","https://openalex.org/W3204019825"],"abstract_inverted_index":{"README.txt":[0],"Title:":[1],"<em>Identifying":[2],"Machine-Paraphrased":[3],"Plagiarism</em><br>":[4],"Authors:":[5],"Jan":[6,565],"Philip":[7,566],"Wahle,":[8],"Terry":[9,569],"Ruas,":[10,568],"Tomas":[11],"Foltynek,":[12],"Norman":[13,576],"Meuschke,":[14,575],"and":[15,141,149,240,262,445,468,499,501,526,567,570,574,577,616,621],"Bela":[16],"Gipp<br>":[17],"contact":[18],"email:":[19],"wahle@gipplab.org;":[20],"ruas@gipplab.org;<br>":[21],"Venue:":[22],"iConference<br>":[23],"Year:":[24],"2022<br>":[25],"================================================================<br>":[26,130],"<strong>Dataset":[27],"Description:</strong>":[28],"<em><strong>Training:</strong></em><br>":[29],"200,767":[30],"paragraphs":[31,453,479],"(98,282":[32],"original,":[33,42],"102,485paraphrased)":[34],"extracted":[35],"from":[36,173,194,480],"8,024":[37],"Wikipedia":[38,68,95,122,399,617],"(English)":[39],"articles":[40,618],"(4,012":[41],"4,012":[43],"paraphrased":[44],"using":[45,460,613],"the":[46,146,153,156,195,205,211,234,268,280,285,340,344,381,404,411,424,428,461,481,506,517,536,543,559,626],"SpinBot":[47,467,498,615],"API).":[48],"<em><strong>Testing:</strong></em><br>":[49],"SpinBot:":[50],"<br>":[51,76,78,103,105,227,371,383,636],"arXiv":[52,79,106,389],"-":[53,55,58,61,63,66,69,71,74,80,82,85,88,90,93,96,98,101,107,109,112,115,117,120,123,125,128,170,183,190,209,351,353,356,359,364,369,385,388,393,398],"Original":[54,62,70,81,89,97,108,116,124],"20,966;":[56,83,110],"Spun":[57,65,73,84,92,100,111,119,127,452],"20,867<br>":[59],"Theses":[60,87,114,394],"5,226;":[64],"3,463<br>":[67],"39,241;":[72,99,126],"40,729<br>":[75],"SpinnerChief-4W:":[77],"21,671<br>":[86],"2,379;":[91,118],"2,941<br>":[94,121],"39,618<br>":[102],"SpinnerChief-2W:":[104],"21,719<br>":[113],"39,697":[129],"Dataset":[131],"Structure:":[132],"<strong>[human_evaluation]</strong>":[133],"folder:":[134],"human":[135,160,180],"evaluation":[136,236],"to":[137,308],"identify":[138],"human-generated":[139],"text":[140,439],"machine-paraphrased":[142],"text.":[143],"It":[144,409],"contains":[145,267,436],"files":[147,231],"(original":[148],"spun)":[150],"as":[151,327],"for":[152,155,166,179,233,274,292,373,407,416,443,455,532,535,554,619],"answer-key":[154],"survey":[157,196],"performed":[158],"with":[159,258,343,366,484],"subjects":[161],"(all":[162],"data":[163],"is":[164,322,337,475,491,509,540,632],"anonymous":[165],"privacy":[167],"reasons).":[168],"NNNNN.txt":[169],"whole":[171],"document":[172,507,620],"which":[174,200],"an":[175],"extract":[176],"was":[177,215],"taken":[178],"evaluation<br>":[181],"key.txt.zip":[182],"information":[184],"about":[185],"each":[186,275,374,417],"case":[187],"(ORIG/SPUN)<br>":[188],"results.xlsx":[189],"raw":[191,438],"results":[192,224],"downloaded":[193],"tool":[197,245],"(the":[198],"extracts":[199],"humans":[201],"judged":[202],"are":[203,256,317,403,457,470],"in":[204,218,339,380,423,493,542,634],"first":[206],"line)<br>":[207],"results-corrected.xlsx":[208],"at":[210,427,447],"very":[212],"beginning,":[213],"there":[214],"a":[216,328,448,555],"mistake":[217],"one":[219,309],"question":[220],"(wrong":[221],"extract).":[222],"These":[223],"were":[225],"excluded.":[226],"<strong>[automated_evaluation]:":[228],"</strong>contains":[229],"all":[230,271],"used":[232,289,336,376,406,419,442,454,631],"automated":[235],"considering":[237],"[spinbot]":[238],"(https://spinbot.com/API)":[239],"[spinnerchief]":[241],"(http://developer.spinnerchief.com/API_Document.aspx).":[242],"Each":[243,277,305,489],"paraphrase":[244],"folder":[246,490],"contains:":[247],"<strong>[corpus]":[248,434],"</strong>and<strong>":[249],"[vectors]</strong>":[250],"sub-folders.":[251],"For":[252,464,609],"[spinnerchief],":[253],"two":[254],"variations":[255],"included,":[257],"4-word-chaging":[259],"ratio":[260],"(default)":[261],"2-word-chaging":[263],"ratio.":[264],"<strong>[vectors]":[265],"sub-folder</strong>":[266],"average":[269],"of":[270,282,284,430],"word":[272,286,333],"vectors":[273,405],"paragraph.":[276],"line":[278],"has":[279],"number":[281],"dimensions":[283],"embeddings":[287],"technique":[288,335,375,418],"(see":[290],"paper":[291,425],"more":[293,487],"details)":[294],"followed":[295],"by":[296,477],"its":[297],"respective":[298],"class":[299],"(i.e.,":[300,495,503],"label":[301],"mg":[302,494],"or":[303,313,486],"og).":[304],"file":[306,341],"belongs":[307],"class,":[310],"either":[311],"\"mg\"":[312],"\"og\".":[314],"The":[315,320,332,451,472,529,629],"values":[316],"comma-separated":[318],"(.csv).":[319],"extension":[321],".arff":[323],"can":[324,377,420],"be":[325,378,421],"read":[326],"normal":[329],".txt":[330],"file.":[331,433],"embedding":[334],"described":[338,541],"name":[342],"following":[345,627],"structure:":[346],"&lt;technique&gt;-&lt;type&gt;-mean-&lt;data&gt;.arff":[347],".":[348],"Where":[349],"<em>&lt;technique&gt;</em>":[350],"d2v":[352],"doc2vec<br>":[354],"google":[355],"word2vec<br>":[357],"fasttextnw":[358],"fastText":[360,365],"without":[361],"subwording<br>":[362,367],"fasttextsw":[363],"glove":[368],"Glove<br>":[370],"Details":[372,415],"found":[379,422],"paper.<br>":[382],"<em>&lt;type&gt;":[384],"</em>":[386],"arxivp":[387],"paragraph":[390,395,400,449,473,518,622],"split<br>":[391,396],"thesisp":[392],"wikip":[397,413],"split":[401,474,508],"(wikipedia_paragraph_vector_train":[402],"training.":[408],"follows":[410],"same":[412],"structure)":[414],"referenced":[426],"start":[429],"this":[431],"README":[432],"sub-folder:</strong>":[435],"de":[437],"(No":[440],"pre-processing)":[441],"train":[444],"test":[446,465],"level.":[450,519],"<strong>training</strong>":[456],"only":[458,515,614],"generated":[459,476],"<strong>SpinBot":[462],"tool</strong>.":[463],"both":[466],"SpinnerChief":[469],"used.":[471],"selecting":[478],"original":[482],"documents":[483],"3":[485],"sentences.":[488],"divided":[492],"machine-generated":[496],"through":[497],"SpinnerChief)":[500],"og":[502],"original-generated":[504],"file).":[505],"not":[510],"avaiable":[511],"since":[512],"our":[513,610],"experiments":[514],"use":[516],"Machine":[520],"Learning":[521],"models:":[522],"SVM,":[523],"Naive":[524],"Bayes,":[525],"Logistic":[527],"Regression.":[528],"grid":[530],"search":[531],"hyperparameter":[533],"adjustments":[534],"machine":[537],"learning":[538],"classifiers":[539],"paper.":[544],"@incollection{WahleRFM22,<br>":[545],"title":[546],"=":[547,552,563,581,585,588,591,594,599,602,605],"{Identifying":[548],"{{Machine-Paraphrased":[549],"Plagiarism}}},<br>":[550],"booktitle":[551],"{Information":[553],"{{Better":[556],"World}}:":[557],"{{Shaping}}":[558],"{{Global":[560],"Future}}},<br>":[561],"author":[562],"{Wahle,":[564],"Folt{\\\u2019y}nek,":[571],"Tom{\\\u2019a}{\\v":[572],"s}":[573],"Gipp,":[578],"Bela},<br>":[579],"editor":[580],"{Smits,":[582],"Malte},<br>":[583],"year":[584],"{2022},<br>":[586],"volume":[587],"{13192},<br>":[589],"pages":[590],"{393--413},<br>":[592],"publisher":[593],"{{Springer":[595],"International":[596],"Publishing}},<br>":[597],"address":[598],"{{Cham}},<br>":[600],"doi":[601],"{10.1007/978-3-030-96957-8_34},<br>":[603],"isbn":[604],"{978-3-030-96956-1":[606],"978-3-030-96957-8},<br>":[607],"}":[608],"previous":[611],"publication":[612],"split,":[623],"please":[624],"see":[625],"publication.":[628],"dataset":[630],"hosted":[633],"DeepBlue":[635]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2021-11-08T00:00:00"}
