{"id":"https://openalex.org/W4367605051","doi":"https://doi.org/10.1145/3592761","title":"Cross-lingual Text Reuse Detection at Document Level for English-Urdu Language Pair","display_name":"Cross-lingual Text Reuse Detection at Document Level for English-Urdu Language Pair","publication_year":2023,"publication_date":"2023-05-01","ids":{"openalex":"https://openalex.org/W4367605051","doi":"https://doi.org/10.1145/3592761"},"language":"en","primary_location":{"id":"doi:10.1145/3592761","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3592761","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044448260","display_name":"Muhammad Sharjeel","orcid":"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"]}],"countries":["PK"],"is_corresponding":true,"raw_author_name":"Muhammad Sharjeel","raw_affiliation_strings":["Department of Computer Science, COMSATS University Islamabad, Lahore Campus, Pakistan, Pakistan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, COMSATS University Islamabad, Lahore Campus, Pakistan, Pakistan","institution_ids":["https://openalex.org/I16076960"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063867136","display_name":"Iqra Muneer","orcid":"https://orcid.org/0000-0002-3953-307X"},"institutions":[{"id":"https://openalex.org/I142732210","display_name":"University of Engineering and Technology Lahore","ror":"https://ror.org/0051w2v06","country_code":"PK","type":"education","lineage":["https://openalex.org/I142732210"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Iqra Muneer","raw_affiliation_strings":["University of Engineering &amp; Technology Lahore, Narowal Campus, Pakistan, Pakistan"],"affiliations":[{"raw_affiliation_string":"University of Engineering &amp; Technology Lahore, Narowal Campus, Pakistan, Pakistan","institution_ids":["https://openalex.org/I142732210"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103007703","display_name":"Sumaira Nosheen","orcid":null},"institutions":[{"id":"https://openalex.org/I59225215","display_name":"Bahria University","ror":"https://ror.org/02v8d7770","country_code":"PK","type":"education","lineage":["https://openalex.org/I59225215"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Sumaira Nosheen","raw_affiliation_strings":["Bahria University, Lahore Campus, Lahore, Pakistan, Pakistan"],"affiliations":[{"raw_affiliation_string":"Bahria University, Lahore Campus, Lahore, Pakistan, Pakistan","institution_ids":["https://openalex.org/I59225215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005027058","display_name":"Rao Muhammad Adeel Nawab","orcid":"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 University Islamabad, Lahore Campus, Lahore, Pakistan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, COMSATS University Islamabad, Lahore Campus, Lahore, 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"},"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":["Lancaster University, Lancaster, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Lancaster University, Lancaster, United Kingdom","institution_ids":["https://openalex.org/I67415387"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5044448260"],"corresponding_institution_ids":["https://openalex.org/I16076960"],"apc_list":null,"apc_paid":null,"fwci":0.6946,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.74662129,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"22","issue":"6","first_page":"1","last_page":"22"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9987999796867371,"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":0.9987999796867371,"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":0.9973999857902527,"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/T11719","display_name":"Data Quality and Management","score":0.9898999929428101,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/urdu","display_name":"Urdu","score":0.9268429279327393},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7667295336723328},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6545435190200806},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6288048028945923},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.5508907437324524},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.4661860167980194},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.44163185358047485},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2514602541923523},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07435208559036255}],"concepts":[{"id":"https://openalex.org/C2777350258","wikidata":"https://www.wikidata.org/wiki/Q1617","display_name":"Urdu","level":2,"score":0.9268429279327393},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7667295336723328},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6545435190200806},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6288048028945923},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.5508907437324524},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.4661860167980194},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.44163185358047485},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2514602541923523},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07435208559036255},{"id":"https://openalex.org/C548081761","wikidata":"https://www.wikidata.org/wiki/Q180388","display_name":"Waste management","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":2,"locations":[{"id":"doi:10.1145/3592761","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3592761","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"},{"id":"pmh:oai:eprints.lancs.ac.uk:194281","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306401916","display_name":"Lancaster EPrints (Lancaster University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67415387","host_organization_name":"Lancaster University","host_organization_lineage":["https://openalex.org/I67415387"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7799999713897705,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W58323294","https://openalex.org/W1566289585","https://openalex.org/W1593271688","https://openalex.org/W1840435438","https://openalex.org/W2028742638","https://openalex.org/W2053154970","https://openalex.org/W2068297964","https://openalex.org/W2093519373","https://openalex.org/W2123442489","https://openalex.org/W2156377393","https://openalex.org/W2250539671","https://openalex.org/W2340381866","https://openalex.org/W2398936787","https://openalex.org/W2493916176","https://openalex.org/W2508023093","https://openalex.org/W2607303097","https://openalex.org/W2612560781","https://openalex.org/W2760392765","https://openalex.org/W2768744233","https://openalex.org/W2799915114","https://openalex.org/W2890484448","https://openalex.org/W2901626577","https://openalex.org/W2905749056","https://openalex.org/W2906230340","https://openalex.org/W2917407787","https://openalex.org/W2921254041","https://openalex.org/W2940542551","https://openalex.org/W2951941824","https://openalex.org/W2963918774","https://openalex.org/W2973088264","https://openalex.org/W3208597397","https://openalex.org/W4220829290","https://openalex.org/W4231444913","https://openalex.org/W4295867992","https://openalex.org/W6666242729"],"related_works":["https://openalex.org/W2610387714","https://openalex.org/W1512718085","https://openalex.org/W2126364050","https://openalex.org/W1484029852","https://openalex.org/W4379525811","https://openalex.org/W4287306395","https://openalex.org/W2771096531","https://openalex.org/W2757524561","https://openalex.org/W2134714056","https://openalex.org/W3021696757"],"abstract_inverted_index":{"In":[0,54],"recent":[1],"years,":[2],"the":[3,13,16,21,67,71,89,94,101,108,120,138,163,169,173,182,185,205,217],"problem":[4],"of":[5,15,23,80,104,110,134,178,184,192,207,246],"Cross-Lingual":[6],"Text":[7],"Reuse":[8,123],"Detection":[9],"(CLTRD)":[10],"has":[11],"gained":[12],"interest":[14],"research":[17,264],"community":[18],"due":[19],"to":[20,45,52,130,194,261],"availability":[22],"large":[24,81,112],"digital":[25],"repositories":[26],"and":[27,38,59,84,157,168,198,232],"automatic":[28,208],"Machine":[29],"Translation":[30,248],"(MT)":[31],"systems.":[32],"These":[33],"systems":[34],"are":[35,241],"readily":[36],"available":[37,260],"openly":[39],"accessible,":[40],"which":[41],"makes":[42],"it":[43,200],"easier":[44],"reuse":[46,117,136,215],"text":[47,116,135,165,171,214],"across":[48],"languages":[49],"but":[50],"hard":[51],"detect.":[53],"previous":[55],"studies,":[56],"different":[57],"corpora":[58,83],"methods":[60,85,193,209],"have":[61],"been":[62],"developed":[63],"for":[64,70,86,88,124,210,224],"CLTRD":[65,87,263],"at":[66,93,137,216],"sentence/passage":[68],"level":[69],"English-Urdu":[72,90],"language":[73,91],"pair.":[74],"However,":[75],"there":[76],"is":[77,107,143,181,258],"a":[78,111,189,244],"lack":[79],"standard":[82],"pair":[92],"document":[95,139,218],"level.":[96,140,219],"To":[97],"overcome":[98],"this":[99,105,179],"limitation,":[100],"significant":[102],"contribution":[103,177],"study":[106,180],"development":[109,206],"benchmark":[113],"cross-lingual":[114,212],"(English-Urdu)":[115,213],"corpus,":[118],"called":[119],"TREU":[121,186,256],"(Text":[122],"English-Urdu)":[125],"corpus.":[126],"It":[127],"contains":[128],"English":[129,167],"Urdu":[131,174],"real":[132],"cases":[133],"The":[141,220,255],"corpus":[142,187,257],"manually":[144],"labelled":[145],"into":[146],"three":[147],"categories":[148],"(Wholly":[149],"Derived":[150,154,159],"=":[151,155,160,230,237],"672,":[152],"Partially":[153],"888,":[156],"Non":[158],"697)":[161],"with":[162],"source":[164],"in":[166,172,204,265],"derived":[170],"language.":[175],"Another":[176],"evaluation":[183,222],"using":[188,243],"diversified":[190],"range":[191],"show":[195],"its":[196],"usefulness":[197],"how":[199],"can":[201],"be":[202],"utilized":[203],"measuring":[211],"best":[221],"results,":[223],"both":[225],"binary":[226],"(":[227,234],"F":[228,235],"1":[229,236],"0.78)":[231],"ternary":[233],"0.66)":[238],"classification":[239],"tasks,":[240],"obtained":[242],"combination":[245],"all":[247],"plus":[249],"Mono-lingual":[250],"Analysis":[251],"(T+MA)":[252],"based":[253],"methods.":[254],"publicly":[259],"promote":[262],"an":[266],"under-resourced":[267],"language,":[268],"i.e.,":[269],"Urdu.":[270]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
