{"id":"https://openalex.org/W2885961833","doi":"https://doi.org/10.1177/0165551518787696","title":"Cross-lingual text alignment for fine-grained plagiarism detection","display_name":"Cross-lingual text alignment for fine-grained plagiarism detection","publication_year":2018,"publication_date":"2018-08-13","ids":{"openalex":"https://openalex.org/W2885961833","doi":"https://doi.org/10.1177/0165551518787696","mag":"2885961833"},"language":"en","primary_location":{"id":"doi:10.1177/0165551518787696","is_oa":false,"landing_page_url":"https://doi.org/10.1177/0165551518787696","pdf_url":null,"source":{"id":"https://openalex.org/S68913162","display_name":"Journal of Information Science","issn_l":"0165-5515","issn":["0165-5515","1741-6485"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Information Science","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/A5000729012","display_name":"Nava Ehsan","orcid":null},"institutions":[{"id":"https://openalex.org/I23946033","display_name":"University of Tehran","ror":"https://ror.org/05vf56z40","country_code":"IR","type":"education","lineage":["https://openalex.org/I23946033"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Nava Ehsan","raw_affiliation_strings":["School of Electrical and Computer Engineering, College of Engineering, University of Tehran, Islamic Republic of Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, College of Engineering, University of Tehran, Islamic Republic of Iran","institution_ids":["https://openalex.org/I23946033"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055494428","display_name":"Azadeh Shakery","orcid":"https://orcid.org/0000-0003-1799-8340"},"institutions":[{"id":"https://openalex.org/I23946033","display_name":"University of Tehran","ror":"https://ror.org/05vf56z40","country_code":"IR","type":"education","lineage":["https://openalex.org/I23946033"]},{"id":"https://openalex.org/I4210146419","display_name":"Institute for Research in Fundamental Sciences","ror":"https://ror.org/04xreqs31","country_code":"IR","type":"facility","lineage":["https://openalex.org/I4210146419"]}],"countries":["IR"],"is_corresponding":true,"raw_author_name":"Azadeh Shakery","raw_affiliation_strings":["School of Computer Science, Institute for Research in Fundamental Sciences (IPM), Islamic Republic of Iran","School of Electrical and Computer Engineering, College of Engineering, University of Tehran, Islamic Republic of Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Institute for Research in Fundamental Sciences (IPM), Islamic Republic of Iran","institution_ids":["https://openalex.org/I4210146419"]},{"raw_affiliation_string":"School of Electrical and Computer Engineering, College of Engineering, University of Tehran, Islamic Republic of Iran","institution_ids":["https://openalex.org/I23946033"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000681085","display_name":"Frank Wm. Tompa","orcid":"https://orcid.org/0000-0002-1907-9535"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Frank Wm Tompa","raw_affiliation_strings":["David R. Cheriton School of Computer Science, University of Waterloo, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"David R. Cheriton School of Computer Science, University of Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5055494428"],"corresponding_institution_ids":["https://openalex.org/I23946033","https://openalex.org/I4210146419"],"apc_list":null,"apc_paid":null,"fwci":1.0151,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.82660632,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"45","issue":"4","first_page":"443","last_page":"459"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9977999925613403,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.9958999752998352,"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/computer-science","display_name":"Computer science","score":0.8670750260353088},{"id":"https://openalex.org/keywords/plagiarism-detection","display_name":"Plagiarism detection","score":0.7659262418746948},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6714553833007812},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6162651181221008},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6132998466491699},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5530892610549927},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.5520977973937988},{"id":"https://openalex.org/keywords/source-text","display_name":"Source text","score":0.5325658917427063},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5156180262565613},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.48559898138046265},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4490193724632263},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.44749778509140015},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.4371541738510132},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11092787981033325}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8670750260353088},{"id":"https://openalex.org/C2780907237","wikidata":"https://www.wikidata.org/wiki/Q2986238","display_name":"Plagiarism detection","level":2,"score":0.7659262418746948},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6714553833007812},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6162651181221008},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6132998466491699},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5530892610549927},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.5520977973937988},{"id":"https://openalex.org/C120012220","wikidata":"https://www.wikidata.org/wiki/Q1754533","display_name":"Source text","level":2,"score":0.5325658917427063},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5156180262565613},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.48559898138046265},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4490193724632263},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.44749778509140015},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4371541738510132},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11092787981033325},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/0165551518787696","is_oa":false,"landing_page_url":"https://doi.org/10.1177/0165551518787696","pdf_url":null,"source":{"id":"https://openalex.org/S68913162","display_name":"Journal of Information Science","issn_l":"0165-5515","issn":["0165-5515","1741-6485"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Information Science","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8100000023841858,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1379526409","display_name":null,"funder_award_id":"CS1397-4-55","funder_id":"https://openalex.org/F4320323645","funder_display_name":"Institute for Research in Fundamental Sciences"}],"funders":[{"id":"https://openalex.org/F4320322667","display_name":"University of Tehran","ror":"https://ror.org/05vf56z40"},{"id":"https://openalex.org/F4320322676","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68"},{"id":"https://openalex.org/F4320323645","display_name":"Institute for Research in Fundamental Sciences","ror":"https://ror.org/04xreqs31"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1498990157","https://openalex.org/W1508037682","https://openalex.org/W1524281572","https://openalex.org/W1553433956","https://openalex.org/W1574901103","https://openalex.org/W1967925097","https://openalex.org/W1970689298","https://openalex.org/W1994500780","https://openalex.org/W2003391098","https://openalex.org/W2019102947","https://openalex.org/W2028776121","https://openalex.org/W2029097226","https://openalex.org/W2105157020","https://openalex.org/W2113403290","https://openalex.org/W2127289991","https://openalex.org/W2131752763","https://openalex.org/W2141824829","https://openalex.org/W2277931188","https://openalex.org/W2343777367","https://openalex.org/W2400223370","https://openalex.org/W2500036977","https://openalex.org/W2608239929","https://openalex.org/W2613959975","https://openalex.org/W2912218307","https://openalex.org/W2912512851","https://openalex.org/W2914349171","https://openalex.org/W2999905431","https://openalex.org/W4213009331","https://openalex.org/W4213169074","https://openalex.org/W4234778484","https://openalex.org/W4248817818","https://openalex.org/W4292760868"],"related_works":["https://openalex.org/W3107474891","https://openalex.org/W1585034923","https://openalex.org/W2435130738","https://openalex.org/W1592339875","https://openalex.org/W2610387714","https://openalex.org/W1512718085","https://openalex.org/W2016908626","https://openalex.org/W4281690070","https://openalex.org/W4293768631","https://openalex.org/W88663061"],"abstract_inverted_index":{"Fast":[0],"and":[1,21,57,96,118,227],"easy":[2],"access":[3],"to":[4,26,29,64,68,90,113,172,185,192,199],"a":[5,38,125,170,181,196],"wide":[6,17],"range":[7],"of":[8,19,153,162,175,179,203],"documents":[9,49,98],"in":[10,13,99,159,224],"various":[11],"languages,":[12],"conjunction":[14],"with":[15],"the":[16,27,69,77,82,87,109,138,144,151,154,204,213,217,221,225],"availability":[18],"translation":[20,183],"editing":[22],"tools,":[23],"has":[24,105],"led":[25],"need":[28],"develop":[30],"effective":[31],"tools":[32],"for":[33,54],"detecting":[34],"cross-lingual":[35,41],"plagiarism.":[36],"Given":[37],"suspicious":[39,70,97],"document,":[40],"plagiarism":[42],"detection":[43],"comprises":[44],"two":[45,106,149],"main":[46,107],"subtasks:":[47],"retrieving":[48],"that":[50,55,135,209,219],"are":[51],"candidate":[52,115],"sources":[53],"document":[56],"analysing":[58],"those":[59],"candidates":[60],"one":[61,63,190],"by":[62,124,140,216],"determine":[65],"their":[66],"similarity":[67,128],"document.":[71],"In":[72,164],"this":[73],"article,":[74],"we":[75],"examine":[76],"second":[78],"subtask,":[79,85],"also":[80],"called":[81],"detailed":[83],"analysis":[84,129],"where":[86],"goal":[88],"is":[89],"align":[91],"plagiarised":[92,116],"fragments":[93,117],"from":[94,189],"source":[95],"different":[100,160],"languages.":[101],"Our":[102],"proposed":[103],"approach":[104,168],"steps:":[108],"first":[110],"step":[111],"tries":[112],"find":[114],"focuses":[119],"on":[120,131],"high":[121],"recall,":[122],"followed":[123],"more":[126],"precise":[127],"based":[130],"dynamic":[132],"text":[133],"alignment":[134],"will":[136,156],"filter":[137],"results":[139,207,223],"finding":[141],"alignments":[142],"between":[143],"identified":[145],"fragments.":[146],"With":[147],"these":[148],"steps,":[150,166],"proximity":[152],"terms":[155,177],"be":[157],"considered":[158],"levels":[161],"granularity.":[163],"both":[165],"our":[167,210],"uses":[169],"dictionary":[171],"obtain":[173],"translations":[174,202],"individual":[176],"instead":[178],"using":[180],"machine":[182],"system":[184],"convert":[186],"longer":[187],"passages":[188],"language":[191],"another.":[193],"We":[194],"used":[195,215],"weighting":[197],"scheme":[198],"distinct":[200],"multiple":[201],"terms.":[205],"Experimental":[206],"show":[208],"method":[211],"outperforms":[212],"methods":[214],"systems":[218],"achieved":[220],"best":[222],"PAN-2012":[226],"PAN-2014":[228],"competitions.":[229]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}