{"id":"https://openalex.org/W4393784688","doi":"https://doi.org/10.5281/zenodo.3251771","title":"Webis Crowd Paraphrase Corpus 2011 (Webis-CPC-11)","display_name":"Webis Crowd Paraphrase Corpus 2011 (Webis-CPC-11)","publication_year":2013,"publication_date":"2013-06-01","ids":{"openalex":"https://openalex.org/W4393784688","doi":"https://doi.org/10.5281/zenodo.3251771"},"language":"en","primary_location":{"id":"pmh:oai:figshare.com:article/8311106","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":"https://openalex.org/A5042650748","display_name":"Steven Burrows","orcid":null},"institutions":[{"id":"https://openalex.org/I51441396","display_name":"Bauhaus-Universit\u00e4t Weimar","ror":"https://ror.org/033bb5z47","country_code":"DE","type":"education","lineage":["https://openalex.org/I51441396"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Burrows, Steven","raw_affiliation_strings":["Bauhaus-Universit\u00e4t Weimar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bauhaus-Universit\u00e4t Weimar","institution_ids":["https://openalex.org/I51441396"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083712311","display_name":"Martin Potthast","orcid":"https://orcid.org/0000-0003-2451-0665"},"institutions":[{"id":"https://openalex.org/I51441396","display_name":"Bauhaus-Universit\u00e4t Weimar","ror":"https://ror.org/033bb5z47","country_code":"DE","type":"education","lineage":["https://openalex.org/I51441396"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Potthast, Martin","raw_affiliation_strings":["Bauhaus-Universit\u00e4t Weimar"],"raw_orcid":"https://orcid.org/0000-0003-2451-0665","affiliations":[{"raw_affiliation_string":"Bauhaus-Universit\u00e4t Weimar","institution_ids":["https://openalex.org/I51441396"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027915931","display_name":"Benno Stein","orcid":"https://orcid.org/0000-0001-9033-2217"},"institutions":[{"id":"https://openalex.org/I51441396","display_name":"Bauhaus-Universit\u00e4t Weimar","ror":"https://ror.org/033bb5z47","country_code":"DE","type":"education","lineage":["https://openalex.org/I51441396"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stein, Benno","raw_affiliation_strings":["Bauhaus-Universit\u00e4t Weimar"],"raw_orcid":"https://orcid.org/0000-0001-9033-2217","affiliations":[{"raw_affiliation_string":"Bauhaus-Universit\u00e4t Weimar","institution_ids":["https://openalex.org/I51441396"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073349957","display_name":"Andreas Eiselt","orcid":null},"institutions":[{"id":"https://openalex.org/I51441396","display_name":"Bauhaus-Universit\u00e4t Weimar","ror":"https://ror.org/033bb5z47","country_code":"DE","type":"education","lineage":["https://openalex.org/I51441396"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Eiselt, Andreas","raw_affiliation_strings":["Bauhaus-Universit\u00e4t Weimar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bauhaus-Universit\u00e4t Weimar","institution_ids":["https://openalex.org/I51441396"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9542999863624573,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9542999863624573,"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":0.967313289642334},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4555164873600006},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4433083236217499},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3546626567840576},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.3253861665725708}],"concepts":[{"id":"https://openalex.org/C2780922921","wikidata":"https://www.wikidata.org/wiki/Q255189","display_name":"Paraphrase","level":2,"score":0.967313289642334},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4555164873600006},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4433083236217499},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3546626567840576},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.3253861665725708}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:figshare.com:article/8311106","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:3251771","is_oa":true,"landing_page_url":"https://zenodo.org/record/3251771","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/other"},{"id":"doi:10.5281/zenodo.3251771","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.3251771","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/8311106","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2748952813","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"],"abstract_inverted_index":{"The":[0,16],"Webis":[1],"Crowd":[2],"Paraphrase":[3],"Corpus":[4],"2011":[5],"(Webis-CPC-11)":[6],"contains":[7],"7,859":[8],"candidate":[9],"paraphrases":[10],"obtained":[11],"from":[12],"Mechanical":[13],"Turk":[14],"crowdsourcing.":[15],"corpus":[17],"is":[18,70],"made":[19],"up":[20],"of":[21,37,52],"4,067":[22],"accepted":[23,109],"paraphrases,":[24],"3,792":[25],"rejected":[26],"non-paraphrases,":[27],"and":[28,86,104],"the":[29,53,58,76,81,96,106],"original":[30,77],"texts.":[31],"These":[32],"samples":[33],"have":[34],"formed":[35],"part":[36],"PAN":[38],"2010":[39],"international":[40],"plagiarism":[41],"detection":[42],"competition,":[43],"but":[44],"were":[45],"not":[46],"previously":[47],"available":[48],"separate":[49],"to":[50],"rest":[51],"competition":[54],"data.":[55],"We":[56],"provide":[57],"dataset":[59],"as":[60],"a":[61,65,87],"single":[62],"folder":[63],"in":[64],"Zip":[66],"archive.":[67],"Each":[68],"paraphrase":[69,82,107],"represented":[71],"by":[72],"three":[73],"files,":[74],"containing":[75,89],"text":[78,83],"(e.g.:":[79,84,91],"\"1-original.txt\"),":[80],"\"1-paraphrase.txt\"),":[85],"file":[88],"metadata":[90],"\"1-metadata.txt\"),":[92],"with":[93],"information":[94],"about":[95],"task":[97,99],"identifier,":[98,101],"author":[100],"time":[102],"taken,":[103],"whether":[105],"was":[108],"or":[110],"rejected.":[111]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}