{"id":"https://openalex.org/W3139157128","doi":"https://doi.org/10.5281/zenodo.4621403","title":"Are Neural Language Models Good Plagiarists? A Benchmark for Neural Paraphrase Detection","display_name":"Are Neural Language Models Good Plagiarists? A Benchmark for Neural Paraphrase Detection","publication_year":2021,"publication_date":"2021-03-19","ids":{"openalex":"https://openalex.org/W3139157128","doi":"https://doi.org/10.5281/zenodo.4621403","mag":"3139157128"},"language":"en","primary_location":{"id":"pmh:oai:figshare.com:article/14252471","is_oa":true,"landing_page_url":"https://figshare.com/articles/dataset/Are_Neural_Language_Models_Good_Plagiarists_A_Benchmark_for_Neural_Paraphrase_Detection/14252471","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":"https://figshare.com/articles/dataset/Are_Neural_Language_Models_Good_Plagiarists_A_Benchmark_for_Neural_Paraphrase_Detection/14252471","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008679414","display_name":"Jan Philip Wahle","orcid":"https://orcid.org/0000-0002-2116-9767"},"institutions":[{"id":"https://openalex.org/I167360494","display_name":"University of Wuppertal","ror":"https://ror.org/00613ak93","country_code":"DE","type":"education","lineage":["https://openalex.org/I167360494"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Wahle, Jan Philip","raw_affiliation_strings":["Bergische Universit\u00e4t Wuppertal"],"raw_orcid":"https://orcid.org/0000-0002-2116-9767","affiliations":[{"raw_affiliation_string":"Bergische Universit\u00e4t Wuppertal","institution_ids":["https://openalex.org/I167360494"]}]},{"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/I167360494","display_name":"University of Wuppertal","ror":"https://ror.org/00613ak93","country_code":"DE","type":"education","lineage":["https://openalex.org/I167360494"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ruas, Terry","raw_affiliation_strings":["Bergische Universit\u00e4t Wuppertal"],"raw_orcid":"https://orcid.org/0000-0002-9440-780X","affiliations":[{"raw_affiliation_string":"Bergische Universit\u00e4t Wuppertal","institution_ids":["https://openalex.org/I167360494"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060549879","display_name":"Norman Meuschke","orcid":"https://orcid.org/0000-0003-4648-8198"},"institutions":[{"id":"https://openalex.org/I167360494","display_name":"University of Wuppertal","ror":"https://ror.org/00613ak93","country_code":"DE","type":"education","lineage":["https://openalex.org/I167360494"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Meuschke, Norman","raw_affiliation_strings":["Bergische Universit\u00e4t Wuppertal"],"raw_orcid":"https://orcid.org/0000-0003-4648-8198","affiliations":[{"raw_affiliation_string":"Bergische Universit\u00e4t Wuppertal","institution_ids":["https://openalex.org/I167360494"]}]},{"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/I167360494","display_name":"University of Wuppertal","ror":"https://ror.org/00613ak93","country_code":"DE","type":"education","lineage":["https://openalex.org/I167360494"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Gipp, Bela","raw_affiliation_strings":["Bergische Universit\u00e4t Wuppertal"],"raw_orcid":"https://orcid.org/0000-0001-6522-3019","affiliations":[{"raw_affiliation_string":"Bergische Universit\u00e4t Wuppertal","institution_ids":["https://openalex.org/I167360494"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I167360494"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":7,"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/T10028","display_name":"Topic Modeling","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9886000156402588,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13629","display_name":"Text Readability and Simplification","score":0.9854000210762024,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/paraphrase","display_name":"Paraphrase","score":0.9514888525009155},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6885747313499451},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5860421657562256},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5725141167640686},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5464311242103577},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4988269805908203},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3500533103942871},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.09933379292488098},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.051764994859695435}],"concepts":[{"id":"https://openalex.org/C2780922921","wikidata":"https://www.wikidata.org/wiki/Q255189","display_name":"Paraphrase","level":2,"score":0.9514888525009155},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6885747313499451},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5860421657562256},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5725141167640686},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5464311242103577},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4988269805908203},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3500533103942871},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.09933379292488098},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.051764994859695435}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:figshare.com:article/14252471","is_oa":true,"landing_page_url":"https://figshare.com/articles/dataset/Are_Neural_Language_Models_Good_Plagiarists_A_Benchmark_for_Neural_Paraphrase_Detection/14252471","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":"doi:10.5281/zenodo.4621403","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.4621403","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/14252471","is_oa":true,"landing_page_url":"https://figshare.com/articles/dataset/Are_Neural_Language_Models_Good_Plagiarists_A_Benchmark_for_Neural_Paraphrase_Detection/14252471","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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8500000238418579}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W131533222","https://openalex.org/W1544505227","https://openalex.org/W2493916176","https://openalex.org/W2579144703","https://openalex.org/W2947813521","https://openalex.org/W2963310665","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2965373594","https://openalex.org/W2980420460","https://openalex.org/W2996573939","https://openalex.org/W3015468748","https://openalex.org/W3030163527","https://openalex.org/W3119997354","https://openalex.org/W3125358881","https://openalex.org/W3138008297"],"related_works":["https://openalex.org/W2978707643","https://openalex.org/W2294233724","https://openalex.org/W4378713476","https://openalex.org/W2169813772","https://openalex.org/W2736149021","https://openalex.org/W2007563177","https://openalex.org/W4248451614","https://openalex.org/W4310803295","https://openalex.org/W1973985309","https://openalex.org/W3132357981"],"abstract_inverted_index":{"Full-Text":[0],"PDF<br>":[1],"Title:":[2],"Are":[3],"Neural":[4,12],"Language":[5,184],"Models":[6],"Good":[7],"Plagiarists?":[8],"A":[9],"Benchmark":[10],"for":[11,236,240,250],"Paraphrase":[13],"Detection<br>":[14],"Authors:":[15],"Jan":[16],"Philip":[17],"Wahle,":[18],"Terry":[19],"Ruas,":[20],"Norman":[21],"Meuschke,":[22],"and":[23,48,182,260,262],"Bela":[24],"Gipp<br>":[25],"Contact":[26],"email:":[27],"wahle@uni-wuppertal.de;":[28],"ruas@uni-wuppertal.de<br>":[29],"Venue:":[30],"JCDL<br>":[31],"Year:":[32],"2021<br>":[33],"================================================================<br>":[34],"<strong>Dataset":[35],"Description:</strong>":[36],"<em><strong>Training:</strong></em><br>":[37],"1,474,230":[38],"aligned":[39],"paragraphs":[40],"(98,282":[41],"original,":[42,237],"1,375,948":[43],"paraphrased":[44,174,195],"with":[45,161,179],"3":[46],"models":[47],"5":[49],"hyperparameter":[50],"configurations":[51],"each":[52,224],"98,282)":[53],"extracted":[54],"from":[55],"4,012":[56],"(English)":[57],"Wikipedia":[58,81,110,138],"articles.":[59],"<em><strong>Testing:</strong></em><br>":[60],"BERT-large":[61],"(cased):":[62,91],"<br>":[63,72,89,92,101,120,129],"arXiv":[64,93,121],"-":[65,67,70,74,76,79,82,84,87,94,96,99,103,105,108,111,113,116,122,124,127,131,133,136,139,141,144],"Original":[66,75,83,95,104,112,123,132,140],"20,966;":[68,71,97,100,125,128],"Paraphrased":[69,78,86,98,107,115,126,135,143],"Theses":[73,102,130],"5,226;":[77,106,134],"5,226;<br>":[80,109,137],"39,241;":[85,114,117,142,145],"39,241;<br>":[88],"RoBERTa-large":[90],"Longformer-large":[118],"(uncased):":[119],"================================================================":[146,217,242],"Dataset":[147],"Structure:":[148],"<strong>[og]</strong>":[149],"folder:":[150],"original.":[151],"The":[152,231],"original":[153],"documents":[154,196],"are":[155],"split":[156],"by":[157],"the":[158,162,177,193,207,211,214,220,248,264,272],"data":[159],"source":[160],"following":[163],"folders:":[164],"<strong>[arxiv]</strong>":[165,200],"<strong>[thesis]</strong>":[166,201],"<strong>[wikipedia]</strong>":[167,202],"<strong>[wikipedia_train]</strong>":[168,203],"<strong>[`model_name`_mlm_prob_`probability`]":[169],"(e.g.,":[170],"bert-large-cased_mlm_prob_0.15):":[171],"</strong>contains":[172],"all":[173],"examples":[175],"using":[176,213],"model":[178],"name":[180],"`model_name`":[181],"Masked":[183],"Modeling":[185],"probability":[186],"`probability`.<br>":[187],"Each":[188],"paraphrase":[189],"model/probability":[190],"folder":[191,222],"contains":[192,206,227,233],"corresponding":[194],"according":[197],"to<strong>":[198],"[of]</strong>:":[199],"hparams.yml":[204,205],"hyperparameters":[208],"to":[209,257,269,276,279],"reconstruct":[210],"dataset":[212],"official":[215],"repository.":[216],"Files:<br>":[218],"On":[219],"lowest":[221],"level,":[223],"`.txt`":[225],"file":[226],"exactly":[228],"one":[229,270],"paragraph.":[230],"filename":[232],"either":[234],"\"ORIG\"":[235],"or":[238],"\"SPUN\"":[239],"paraphrased.":[241],"Code:<br>":[243],"To":[244],"avoid":[245],"misuse":[246],"of":[247,271],"code":[249],"constructing":[251],"machine-paraphrased":[252],"plagiarism,":[253],"you":[254],"must":[255],"consent":[256],"our":[258,280],"Terms":[259],"Conditions":[261],"send":[263],"signed":[265],"version":[266],"via":[267],"mail":[268],"contact":[273],"addresses":[274],"above":[275],"obtain":[277],"access":[278],"repository":[281],"(see":[282],"TermsAndConditions.pdf).":[283]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-08-08T01:25:22.217667","created_date":"2025-10-10T00:00:00"}