{"id":"https://openalex.org/W4293173291","doi":"https://doi.org/10.52547/jist.33583.10.39.169","title":"A Corpus for Evaluation of Cross Language Text Re-use Detection Systems","display_name":"A Corpus for Evaluation of Cross Language Text Re-use Detection Systems","publication_year":2022,"publication_date":"2022-08-03","ids":{"openalex":"https://openalex.org/W4293173291","doi":"https://doi.org/10.52547/jist.33583.10.39.169"},"language":"en","primary_location":{"id":"doi:10.52547/jist.33583.10.39.169","doi":"https://doi.org/10.52547/jist.33583.10.39.169","is_oa":true,"landing_page_url":"https://doi.org/10.52547/jist.33583.10.39.169","pdf_url":"http://jist.ir/Article/Download/33583","source":{"id":"https://openalex.org/S4210171124","display_name":"Journal of Information Systems and Telecommunication (JIST)","issn_l":"2322-1437","issn":["2322-1437","2345-2773"],"is_oa":true,"is_in_doaj":true,"is_core":false,"listed_in":["doaj","poland-20","russia-white-list-4"],"host_organization":"https://openalex.org/P4310319113","host_organization_name":"The Academic Center for Education, Culture and Research","host_organization_lineage":["https://openalex.org/P4310319113"],"host_organization_lineage_names":["The Academic Center for Education, Culture and Research"],"type":"journal"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Information Systems and Telecommunication (JIST)","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://jist.ir/Article/Download/33583","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001930588","display_name":"Salar Mohtaj","orcid":"https://orcid.org/0000-0002-0032-3833","observed_orcids":["https://orcid.org/0000-0002-0032-3833"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Salar Mohtaj","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5073073246","display_name":"Habibollah Asghari","orcid":"https://orcid.org/0000-0001-9660-8595","observed_orcids":["https://orcid.org/0000-0001-9660-8595"]},"institutions":[{"id":"https://openalex.org/I2802694670","display_name":"Academic Center for Education, Culture and Research","ror":"https://ror.org/0126z4b94","country_code":"IR","type":"nonprofit","lineage":["https://openalex.org/I2802694670"]},{"id":"https://openalex.org/I4210102178","display_name":"ICT Research Institute","ror":"https://ror.org/01a3g2z22","country_code":"IR","type":"facility","lineage":["https://openalex.org/I4210102178"]},{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE","IR"],"is_corresponding":true,"raw_author_name":"Habibollah Asghari","raw_affiliation_strings":[". Faculty IV, Technische University Berlin, Germany",". ICT Research Institute, ACECR, Tehran, Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":". Faculty IV, Technische University Berlin, Germany","institution_ids":["https://openalex.org/I4577782"]},{"raw_affiliation_string":". ICT Research Institute, ACECR, Tehran, Iran","institution_ids":["https://openalex.org/I2802694670","https://openalex.org/I4210102178"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5073073246"],"corresponding_institution_ids":["https://openalex.org/I2802694670","https://openalex.org/I4210102178","https://openalex.org/I4577782"],"apc_list":{"value":100,"currency":"USD","value_usd":100},"apc_paid":{"value":100,"currency":"USD","value_usd":100},"fwci":1.1578,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.822443,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"10","issue":"39","first_page":"169","last_page":"179"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11492","display_name":"Academic integrity and plagiarism","score":0.7685999870300293,"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":0.7685999870300293,"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":0.1143999993801117,"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/T10028","display_name":"Topic Modeling","score":0.014499999582767487,"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/corpus-construction","display_name":"corpus construction","score":0.7160000205039978},{"id":"https://openalex.org/keywords/low-resource-languages","display_name":"low-resource languages","score":0.9399999976158142},{"id":"https://openalex.org/keywords/paraphrasing","display_name":"paraphrase","score":0.7319999933242798},{"id":"https://openalex.org/keywords/wikipedia","display_name":"Wikipedia","score":0.6159999966621399}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8323817253112793},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7300613522529602},{"id":"https://openalex.org/C2780907237","wikidata":"https://www.wikidata.org/wiki/Q2986238","display_name":"Plagiarism detection","level":2,"score":0.6767809391021729},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6267669200897217},{"id":"https://openalex.org/C2776527531","wikidata":"https://www.wikidata.org/wiki/Q9168","display_name":"Persian","level":2,"score":0.5576069951057434},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4783860445022583},{"id":"https://openalex.org/C2474386","wikidata":"https://www.wikidata.org/wiki/Q461183","display_name":"Text corpus","level":2,"score":0.45817041397094727},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.44333091378211975},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.416789710521698},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.40046632289886475},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.32593488693237305},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2720814347267151},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08356383442878723},{"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:10.52547/jist.33583.10.39.169","doi":"https://doi.org/10.52547/jist.33583.10.39.169","is_oa":true,"landing_page_url":"https://doi.org/10.52547/jist.33583.10.39.169","pdf_url":"http://jist.ir/Article/Download/33583","source":{"id":"https://openalex.org/S4210171124","display_name":"Journal of Information Systems and Telecommunication (JIST)","issn_l":"2322-1437","issn":["2322-1437","2345-2773"],"is_oa":true,"is_in_doaj":true,"is_core":false,"listed_in":["doaj","poland-20","russia-white-list-4"],"host_organization":"https://openalex.org/P4310319113","host_organization_name":"The Academic Center for Education, Culture and Research","host_organization_lineage":["https://openalex.org/P4310319113"],"host_organization_lineage_names":["The Academic Center for Education, Culture and Research"],"type":"journal"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Information Systems and Telecommunication (JIST)","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.52547/jist.33583.10.39.169","doi":"https://doi.org/10.52547/jist.33583.10.39.169","is_oa":true,"landing_page_url":"https://doi.org/10.52547/jist.33583.10.39.169","pdf_url":"http://jist.ir/Article/Download/33583","source":{"id":"https://openalex.org/S4210171124","display_name":"Journal of Information Systems and Telecommunication (JIST)","issn_l":"2322-1437","issn":["2322-1437","2345-2773"],"is_oa":true,"is_in_doaj":true,"is_core":false,"listed_in":["doaj","poland-20","russia-white-list-4"],"host_organization":"https://openalex.org/P4310319113","host_organization_name":"The Academic Center for Education, Culture and Research","host_organization_lineage":["https://openalex.org/P4310319113"],"host_organization_lineage_names":["The Academic Center for Education, Culture and Research"],"type":"journal"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Information Systems and Telecommunication (JIST)","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320323057","display_name":"Academic Center for Education, Culture and Research","ror":"https://ror.org/0126z4b94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4293173291.pdf","grobid_xml":"https://content.openalex.org/works/W4293173291.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W13806629","https://openalex.org/W14574270","https://openalex.org/W1489181569","https://openalex.org/W1496503889","https://openalex.org/W1504406162","https://openalex.org/W1508037682","https://openalex.org/W1544505227","https://openalex.org/W1880085624","https://openalex.org/W1974336599","https://openalex.org/W1981522058","https://openalex.org/W2019102947","https://openalex.org/W2028776121","https://openalex.org/W2105180486","https://openalex.org/W2145080939","https://openalex.org/W2164998314","https://openalex.org/W2186267129","https://openalex.org/W2251179870","https://openalex.org/W2325518403","https://openalex.org/W2806746267","https://openalex.org/W2905907858","https://openalex.org/W2945673882","https://openalex.org/W3010889635","https://openalex.org/W4249102193","https://openalex.org/W6986298011","https://openalex.org/W7004726404"],"related_works":["https://openalex.org/W2921254041","https://openalex.org/W7128324320","https://openalex.org/W2996549131","https://openalex.org/W2394881938","https://openalex.org/W2945673882","https://openalex.org/W2028776121","https://openalex.org/W3037895534","https://openalex.org/W2508605429","https://openalex.org/W2131752763","https://openalex.org/W2617604077"],"abstract_inverted_index":{"In":[0,113,173],"recent":[1],"years,":[2],"the":[3,8,25,35,71,90,177,189],"availability":[4],"of":[5,73,92,140],"documents":[6,65],"through":[7],"Internet":[9],"along":[10],"with":[11,137],"automatic":[12,47],"translation":[13],"systems":[14,75],"have":[15,53,95,106,158],"increased":[16],"plagiarism,":[17],"especially":[18],"across":[19,51],"languages.":[20,112,172],"Cross-lingual":[21],"plagiarism":[22,67,87,125,203],"occurs":[23],"when":[24],"source":[26],"or":[27,37],"original":[28],"text":[29,39,48,161],"is":[30,40,58,209],"in":[31,41,63,155],"one":[32],"language":[33,103],"and":[34,76,100,105,151,182,211],"plagiarized":[36,143],"re-used":[38],"another":[42],"language.":[43],"Various":[44],"methods":[45,185],"for":[46,66,120,200,214],"re-use":[49],"detection":[50,88,126,204],"languages":[52],"been":[54],"developed":[55],"whose":[56],"objective":[57],"to":[59,98,157,169,175],"assist":[60],"human":[61],"experts":[62],"analyzing":[64],"cases.":[68],"For":[69],"evaluating":[70],"performance":[72],"these":[74],"algorithms,":[77],"standard":[78],"evaluation":[79,184,198],"resources":[80],"are":[81,145],"needed.":[82],"To":[83],"construct":[84],"cross":[85],"lingual":[86],"corpora,":[89],"majority":[91],"earlier":[93],"studies":[94],"paid":[96],"attention":[97],"English":[99,150],"other":[101,170],"European":[102],"pairs,":[104],"less":[107],"focused":[108],"on":[109,129],"low":[110],"resource":[111],"this":[114],"paper,":[115],"we":[116],"investigate":[117],"a":[118],"method":[119],"constructing":[121],"an":[122,197],"English-Persian":[123],"cross-language":[124,202],"corpus":[127,191,208],"based":[128],"parallel":[130],"bilingual":[131],"sentences":[132],"that":[133],"arti\ufb01cially":[134],"generate":[135],"passages":[136,144],"various":[138],"degrees":[139],"paraphrasing.":[141],"The":[142,163],"inserted":[146],"into":[147,196],"topically":[148],"related":[149],"Persian":[152],"Wikipedia":[153],"articles":[154],"order":[156,174],"more":[159],"realistic":[160],"documents.":[162],"proposed":[164,207],"approach":[165],"can":[166,192],"be":[167,193],"applied":[168],"less-resourced":[171],"evaluate":[176],"compiled":[178,190],"corpus,":[179],"both":[180],"intrinsic":[181],"extrinsic":[183],"were":[186],"employed.":[187],"So,":[188],"suitably":[194],"included":[195],"framework":[199],"assessing":[201],"systems.":[205],"Our":[206],"free":[210],"publicly":[212],"available":[213],"research":[215],"purposes.":[216]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2022-08-27T00:00:00"}
