{"id":"https://openalex.org/W2901626577","doi":"https://doi.org/10.1002/asi.24074","title":"CLEU \u2010 A Cross\u2010language english\u2010urdu corpus and benchmark for text reuse experiments","display_name":"CLEU \u2010 A Cross\u2010language english\u2010urdu corpus and benchmark for text reuse experiments","publication_year":2018,"publication_date":"2018-11-19","ids":{"openalex":"https://openalex.org/W2901626577","doi":"https://doi.org/10.1002/asi.24074","mag":"2901626577"},"language":"en","primary_location":{"id":"doi:10.1002/asi.24074","doi":"https://doi.org/10.1002/asi.24074","is_oa":true,"landing_page_url":"https://doi.org/10.1002/asi.24074","pdf_url":null,"source":{"id":"https://openalex.org/S4210197613","display_name":"Journal of the Association for Information Science and Technology","issn_l":"2330-1635","issn":["2330-1635","2330-1643"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","ccf-b","cwts-core","dongbi-b","erih-plus","fnege-4","jufo-3","ki-jl-1","norway-2","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the Association for Information Science and Technology","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1002/asi.24074","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063867136","display_name":"Iqra Muneer","orcid":"https://orcid.org/0000-0002-3953-307X","observed_orcids":["https://orcid.org/0000-0002-3953-307X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Iqra Muneer","raw_affiliation_strings":["Department of Computer Science, Rachna College of Engineering and Technology, Pakistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Rachna College of Engineering and Technology, Pakistan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044448260","display_name":"Muhammad Sharjeel","orcid":"https://orcid.org/0000-0003-3361-4335","observed_orcids":["https://orcid.org/0000-0003-3361-4335"]},"institutions":[{"id":"https://openalex.org/I16076960","display_name":"COMSATS University Islamabad","ror":"https://ror.org/00nqqvk19","country_code":"PK","type":"education","lineage":["https://openalex.org/I16076960"]},{"id":"https://openalex.org/I67415387","display_name":"Lancaster University","ror":"https://ror.org/04f2nsd36","country_code":"GB","type":"education","lineage":["https://openalex.org/I67415387"]}],"countries":["GB","PK"],"is_corresponding":false,"raw_author_name":"Muhammad Sharjeel","raw_affiliation_strings":["Department of Computer Science, COMSATS Institute of Information Technology, Pakistan","School of Computing and Communications, Lancaster University, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, COMSATS Institute of Information Technology, Pakistan","institution_ids":["https://openalex.org/I16076960"]},{"raw_affiliation_string":"School of Computing and Communications, Lancaster University, UK","institution_ids":["https://openalex.org/I67415387"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005033313","display_name":"Muntaha Iqbal","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I16076960","display_name":"COMSATS University Islamabad","ror":"https://ror.org/00nqqvk19","country_code":"PK","type":"education","lineage":["https://openalex.org/I16076960"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Muntaha Iqbal","raw_affiliation_strings":["Department of Computer Science, COMSATS Institute of Information Technology, Pakistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, COMSATS Institute of Information Technology, Pakistan","institution_ids":["https://openalex.org/I16076960"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005027058","display_name":"Rao Muhammad Adeel Nawab","orcid":"https://orcid.org/0000-0002-1765-8904","observed_orcids":["https://orcid.org/0000-0002-1765-8904"]},"institutions":[{"id":"https://openalex.org/I16076960","display_name":"COMSATS University Islamabad","ror":"https://ror.org/00nqqvk19","country_code":"PK","type":"education","lineage":["https://openalex.org/I16076960"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Rao Muhammad Adeel Nawab","raw_affiliation_strings":["Department of Computer Science, COMSATS Institute of Information Technology, Pakistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, COMSATS Institute of Information Technology, Pakistan","institution_ids":["https://openalex.org/I16076960"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058785189","display_name":"Paul Rayson","orcid":"https://orcid.org/0000-0002-1257-2191","observed_orcids":["https://orcid.org/0000-0002-1257-2191"]},"institutions":[{"id":"https://openalex.org/I67415387","display_name":"Lancaster University","ror":"https://ror.org/04f2nsd36","country_code":"GB","type":"education","lineage":["https://openalex.org/I67415387"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Paul Rayson","raw_affiliation_strings":["School of Computing and Communications, Lancaster University, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Communications, Lancaster University, UK","institution_ids":["https://openalex.org/I67415387"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":3310,"currency":"USD","value_usd":3310},"apc_paid":{"value":3310,"currency":"USD","value_usd":3310},"fwci":1.9927,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.89726764,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":"70","issue":"7","first_page":"729","last_page":"741"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11492","display_name":"Academic integrity and plagiarism","score":0.5386000275611877,"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":0.5386000275611877,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.10999999940395355,"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/T10260","display_name":"Software Engineering Research","score":0.06759999692440033,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/text-reuse-detection","display_name":"text reuse detection","score":0.902999997138977},{"id":"https://openalex.org/keywords/multilingual-web-content","display_name":"multilingual web content","score":0.6819999814033508},{"id":"https://openalex.org/keywords/gold-standard-corpus","display_name":"gold standard corpus","score":0.597000002861023},{"id":"https://openalex.org/keywords/paraphrase-detection","display_name":"paraphrase detection","score":0.6389999985694885},{"id":"https://openalex.org/keywords/benchmark-dataset","display_name":"benchmark dataset","score":0.37700000405311584}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8024325370788574},{"id":"https://openalex.org/C2777350258","wikidata":"https://www.wikidata.org/wiki/Q1617","display_name":"Urdu","level":2,"score":0.7570022940635681},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6157706379890442},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6145713329315186},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.6056560277938843},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5398321747779846},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.4953095018863678},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4795382022857666},{"id":"https://openalex.org/C2780505938","wikidata":"https://www.wikidata.org/wiki/Q17093282","display_name":"Unavailability","level":2,"score":0.42215076088905334},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2020559012889862},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14877906441688538},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08399876952171326},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07661888003349304},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1002/asi.24074","doi":"https://doi.org/10.1002/asi.24074","is_oa":true,"landing_page_url":"https://doi.org/10.1002/asi.24074","pdf_url":null,"source":{"id":"https://openalex.org/S4210197613","display_name":"Journal of the Association for Information Science and Technology","issn_l":"2330-1635","issn":["2330-1635","2330-1643"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","ccf-b","cwts-core","dongbi-b","erih-plus","fnege-4","jufo-3","ki-jl-1","norway-2","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the Association for Information Science and Technology","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1002/asi.24074","doi":"https://doi.org/10.1002/asi.24074","is_oa":true,"landing_page_url":"https://doi.org/10.1002/asi.24074","pdf_url":null,"source":{"id":"https://openalex.org/S4210197613","display_name":"Journal of the Association for Information Science and Technology","issn_l":"2330-1635","issn":["2330-1635","2330-1643"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","ccf-b","cwts-core","dongbi-b","erih-plus","fnege-4","jufo-3","ki-jl-1","norway-2","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the Association for Information Science and Technology","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G5303011379","display_name":null,"funder_award_id":"EP/R00692X/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W13806629","https://openalex.org/W58323294","https://openalex.org/W86855850","https://openalex.org/W366812178","https://openalex.org/W583499102","https://openalex.org/W1496503889","https://openalex.org/W1518684876","https://openalex.org/W1556415388","https://openalex.org/W1574855751","https://openalex.org/W1574901103","https://openalex.org/W1967043694","https://openalex.org/W1967925097","https://openalex.org/W1974336599","https://openalex.org/W2028776121","https://openalex.org/W2037789405","https://openalex.org/W2053154970","https://openalex.org/W2083862165","https://openalex.org/W2105180486","https://openalex.org/W2131752763","https://openalex.org/W2134168908","https://openalex.org/W2148578434","https://openalex.org/W2164777277","https://openalex.org/W2251338372","https://openalex.org/W2251717550","https://openalex.org/W2409439155","https://openalex.org/W2500036977","https://openalex.org/W2508023093","https://openalex.org/W2508605429","https://openalex.org/W2538807767","https://openalex.org/W2905907858","https://openalex.org/W3098382078","https://openalex.org/W6603477831"],"related_works":["https://openalex.org/W7046003663","https://openalex.org/W4367605051","https://openalex.org/W4295867992","https://openalex.org/W4220829290","https://openalex.org/W3208597397","https://openalex.org/W2508023093","https://openalex.org/W2394881938","https://openalex.org/W2508605429","https://openalex.org/W4400949908","https://openalex.org/W2768744233"],"abstract_inverted_index":{"Text":[0],"reuse":[1,38,78,193],"is":[2,15,54,99,115,159,179],"becoming":[3],"a":[4,73,125,180],"serious":[5],"issue":[6],"in":[7,28,93,100,104],"many":[8],"fields":[9],"and":[10,120,188],"research":[11],"shows":[12],"that":[13,114,157],"it":[14,21,158],"much":[16],"harder":[17,160],"to":[18,39,48,145,161],"detect":[19,49,162],"when":[20,170],"occurs":[22],"across":[23],"languages.":[24],"The":[25,85,177],"recent":[26],"rise":[27],"multi\u2010lingual":[29],"content":[30],"on":[31,64,141],"the":[32,55,81,96,130,142,171,185,197],"Web":[33],"has":[34,90],"increased":[35],"cross\u2010language":[36,74,163,191],"text":[37,77,92,98,167,192],"an":[40],"unprecedented":[41],"scale.":[42],"Although":[43],"researchers":[44],"have":[45,174],"proposed":[46,143],"methods":[47],"it,":[50],"one":[51],"major":[52],"drawback":[53],"unavailability":[56],"of":[57,139,166,190],"large\u2010scale":[58],"gold":[59],"standard":[60],"evaluation":[61],"resources":[62],"built":[63],"real":[65,164],"cases.":[66],"To":[67],"overcome":[68],"this":[69],"problem,":[70],"we":[71,128],"propose":[72],"sentence/passage":[75,107],"level":[76],"corpus":[79,178],"for":[80,184,196],"English\u2010Urdu":[82,87,198],"language":[83,172,199],"pair.":[84,200],"Cross\u2010Language":[86],"Corpus":[88],"(CLEU)":[89],"source":[91],"English":[94],"whereas":[95],"derived":[97],"Urdu.":[101],"It":[102],"contains":[103],"total":[105],"3,235":[106],"pairs":[108,173],"manually":[109],"tagged":[110],"into":[111],"three":[112,137],"categories":[113],"near":[116],"copy,":[117,119],"paraphrased":[118],"independently":[121],"written.":[122],"Further,":[123],"as":[124],"second":[126],"contribution,":[127],"evaluate":[129],"Translation":[131],"plus":[132],"Mono\u2010lingual":[133],"Analysis":[134],"method":[135],"using":[136],"sets":[138],"experiments":[140],"dataset":[144],"highlight":[146],"its":[147],"usefulness.":[148],"Evaluation":[149],"results":[150],"(f1=0.732":[151],"binary,":[152],"f1=0.552":[153],"ternary":[154],"classification)":[155],"indicate":[156],"cases":[165],"reuse,":[168],"especially":[169],"unrelated":[175],"scripts.":[176],"useful":[181],"benchmark":[182],"resource":[183],"future":[186],"development":[187],"assessment":[189],"detection":[194],"systems":[195]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2018-11-29T00:00:00"}
