{"id":"https://openalex.org/W4318186670","doi":"https://doi.org/10.1109/bigdata55660.2022.10020403","title":"Saisiyat Is Where It Is At! Insights Into Backdoors And Debiasing Of Cross Lingual Transformers For Named Entity Recognition","display_name":"Saisiyat Is Where It Is At! Insights Into Backdoors And Debiasing Of Cross Lingual Transformers For Named Entity Recognition","publication_year":2022,"publication_date":"2022-12-17","ids":{"openalex":"https://openalex.org/W4318186670","doi":"https://doi.org/10.1109/bigdata55660.2022.10020403"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata55660.2022.10020403","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/bigdata55660.2022.10020403","pdf_url":null,"source":{"id":"https://openalex.org/S4363607709","display_name":"2022 IEEE International Conference on Big Data (Big Data)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-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/A5041560944","display_name":"Ricardo A. Calix","orcid":null},"institutions":[{"id":"https://openalex.org/I117015748","display_name":"Purdue University Northwest","ror":"https://ror.org/04keq6987","country_code":"US","type":"education","lineage":["https://openalex.org/I117015748"]},{"id":"https://openalex.org/I38260057","display_name":"In-Q-Tel","ror":"https://ror.org/02qp5k481","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I38260057"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ricardo A. Calix","raw_affiliation_strings":["IQT Labs","Purdue University Northwest"],"affiliations":[{"raw_affiliation_string":"IQT Labs","institution_ids":["https://openalex.org/I38260057"]},{"raw_affiliation_string":"Purdue University Northwest","institution_ids":["https://openalex.org/I117015748"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071140661","display_name":"Jj Ben-Joseph","orcid":null},"institutions":[{"id":"https://openalex.org/I38260057","display_name":"In-Q-Tel","ror":"https://ror.org/02qp5k481","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I38260057"]},{"id":"https://openalex.org/I79272384","display_name":"University of Maryland, Baltimore County","ror":"https://ror.org/02qskvh78","country_code":"US","type":"education","lineage":["https://openalex.org/I79272384"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jj Ben-Joseph","raw_affiliation_strings":["IQT Labs","University of Maryland, Baltimore County"],"affiliations":[{"raw_affiliation_string":"IQT Labs","institution_ids":["https://openalex.org/I38260057"]},{"raw_affiliation_string":"University of Maryland, Baltimore County","institution_ids":["https://openalex.org/I79272384"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064769201","display_name":"Nina Lopatina","orcid":"https://orcid.org/0000-0001-6844-4941"},"institutions":[{"id":"https://openalex.org/I38260057","display_name":"In-Q-Tel","ror":"https://ror.org/02qp5k481","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I38260057"]},{"id":"https://openalex.org/I117015748","display_name":"Purdue University Northwest","ror":"https://ror.org/04keq6987","country_code":"US","type":"education","lineage":["https://openalex.org/I117015748"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nina Lopatina","raw_affiliation_strings":["IQT Labs","Purdue University Northwest"],"affiliations":[{"raw_affiliation_string":"IQT Labs","institution_ids":["https://openalex.org/I38260057"]},{"raw_affiliation_string":"Purdue University Northwest","institution_ids":["https://openalex.org/I117015748"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112191704","display_name":"Ryan Ashley","orcid":null},"institutions":[{"id":"https://openalex.org/I38260057","display_name":"In-Q-Tel","ror":"https://ror.org/02qp5k481","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I38260057"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ryan Ashley","raw_affiliation_strings":["IQT Labs"],"affiliations":[{"raw_affiliation_string":"IQT Labs","institution_ids":["https://openalex.org/I38260057"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076629280","display_name":"Mona Gogia","orcid":null},"institutions":[{"id":"https://openalex.org/I38260057","display_name":"In-Q-Tel","ror":"https://ror.org/02qp5k481","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I38260057"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mona Gogia","raw_affiliation_strings":["IQT Labs"],"affiliations":[{"raw_affiliation_string":"IQT Labs","institution_ids":["https://openalex.org/I38260057"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031186503","display_name":"George P. Sieniawski","orcid":null},"institutions":[{"id":"https://openalex.org/I38260057","display_name":"In-Q-Tel","ror":"https://ror.org/02qp5k481","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I38260057"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"George Sieniawski","raw_affiliation_strings":["IQT Labs"],"affiliations":[{"raw_affiliation_string":"IQT Labs","institution_ids":["https://openalex.org/I38260057"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091125067","display_name":"Andrea Brennen","orcid":null},"institutions":[{"id":"https://openalex.org/I38260057","display_name":"In-Q-Tel","ror":"https://ror.org/02qp5k481","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I38260057"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrea Brennen","raw_affiliation_strings":["IQT Labs"],"affiliations":[{"raw_affiliation_string":"IQT Labs","institution_ids":["https://openalex.org/I38260057"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5041560944"],"corresponding_institution_ids":["https://openalex.org/I117015748","https://openalex.org/I38260057"],"apc_list":null,"apc_paid":null,"fwci":0.2081,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.45843883,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2940","last_page":"2949"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":1.0,"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":1.0,"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":0.9987999796867371,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9970999956130981,"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/interpretability","display_name":"Interpretability","score":0.8750947117805481},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7816293239593506},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7209219932556152},{"id":"https://openalex.org/keywords/debiasing","display_name":"Debiasing","score":0.6946021318435669},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.6002693772315979},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.593471884727478},{"id":"https://openalex.org/keywords/backdoor","display_name":"Backdoor","score":0.5476202368736267},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5216617584228516},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5148743391036987},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4906848669052124},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.43260452151298523},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.4293639361858368},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.2583619952201843},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.08086636662483215}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.8750947117805481},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7816293239593506},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7209219932556152},{"id":"https://openalex.org/C2779458634","wikidata":"https://www.wikidata.org/wiki/Q24963715","display_name":"Debiasing","level":2,"score":0.6946021318435669},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.6002693772315979},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.593471884727478},{"id":"https://openalex.org/C2781045450","wikidata":"https://www.wikidata.org/wiki/Q254569","display_name":"Backdoor","level":2,"score":0.5476202368736267},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5216617584228516},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5148743391036987},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4906848669052124},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.43260452151298523},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.4293639361858368},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2583619952201843},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.08086636662483215},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata55660.2022.10020403","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/bigdata55660.2022.10020403","pdf_url":null,"source":{"id":"https://openalex.org/S4363607709","display_name":"2022 IEEE International Conference on Big Data (Big Data)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W2905526464","https://openalex.org/W2913954081","https://openalex.org/W2914304175","https://openalex.org/W2962739339","https://openalex.org/W2962784628","https://openalex.org/W2963250244","https://openalex.org/W2963524349","https://openalex.org/W2963859254","https://openalex.org/W2963979492","https://openalex.org/W2965373594","https://openalex.org/W2971015127","https://openalex.org/W2974817986","https://openalex.org/W3015529893","https://openalex.org/W3035390927","https://openalex.org/W3040711047","https://openalex.org/W3104502698","https://openalex.org/W3104591237","https://openalex.org/W3105882417","https://openalex.org/W3123340107","https://openalex.org/W3123856867","https://openalex.org/W3134678353","https://openalex.org/W3134983687","https://openalex.org/W3135734416","https://openalex.org/W3155429205","https://openalex.org/W3175136611","https://openalex.org/W3183195595","https://openalex.org/W3186056917","https://openalex.org/W3198772699","https://openalex.org/W3201704168","https://openalex.org/W3210339706","https://openalex.org/W3210951978","https://openalex.org/W3212213895","https://openalex.org/W3214210379","https://openalex.org/W4224052067","https://openalex.org/W4285183888","https://openalex.org/W4287691524","https://openalex.org/W4288057740","https://openalex.org/W4313227190","https://openalex.org/W4385245566","https://openalex.org/W6766673545","https://openalex.org/W6767301565","https://openalex.org/W6774548214","https://openalex.org/W6775715944","https://openalex.org/W6781700032","https://openalex.org/W6785887628","https://openalex.org/W6796638215","https://openalex.org/W6799064937","https://openalex.org/W6802927286","https://openalex.org/W6802963051","https://openalex.org/W6802967257","https://openalex.org/W6803064041","https://openalex.org/W6803855868","https://openalex.org/W6804323144","https://openalex.org/W6810319722","https://openalex.org/W6810624030"],"related_works":["https://openalex.org/W4250494529","https://openalex.org/W1964783010","https://openalex.org/W2399696375","https://openalex.org/W45206245","https://openalex.org/W2211396092","https://openalex.org/W2061834489","https://openalex.org/W3088215229","https://openalex.org/W2078793151","https://openalex.org/W3047727388","https://openalex.org/W2759598007"],"abstract_inverted_index":{"Deep":[0],"learning":[1,183],"and,":[2],"in":[3,88,164,187,219,257],"particular,":[4],"Transformer-based":[5],"models":[6,17,202],"are":[7,270],"revolutionizing":[8],"natural":[9],"language":[10],"processing":[11],"(NLP).":[12],"As":[13,242],"a":[14,89,107,193,220,244,259,263],"result,":[15],"NLP":[16],"can":[18,224],"now":[19],"be":[20],"pre-trained":[21],"and":[22,29,49,60,66,79,140,147,179,250,262,272],"fine-tuned":[23],"by":[24,210],"anyone":[25],"with":[26,32],"sufficient":[27],"resources,":[28],"subsequently":[30],"shared":[31],"the":[33,45,114,117,165,212,215,231,235,255],"world":[34],"at":[35],"large.":[36],"This":[37,68],"is":[38,86,160,184],"an":[39],"unprecedented":[40],"approach":[41,57],"that":[42,112,157,171,180,228,252],"helps":[43],"level":[44],"AI":[46,55],"playing":[47],"field":[48],"improves":[50],"productivity.":[51],"However,":[52],"this":[53,128],"new":[54],"sharing":[56],"presents":[58],"novel":[59],"largely":[61],"unaddressed":[62],"challenges":[63],"involving":[64],"bias":[65,87],"backdoors.":[67],"study":[69],"has":[70],"four":[71],"objectives":[72],"related":[73,173],"to":[74,135],"better":[75],"understanding":[76],"these":[77],"issues":[78],"their":[80],"causes:":[81],"1)":[82],"determine":[83],"if":[84],"there":[85],"cross":[90],"lingual":[91],"(XL)":[92],"Transformer":[93,188,201,221],"model":[94,119,236],"such":[95],"as":[96],"RoBERTa":[97],"XLM":[98],"(XLM-R)":[99],"for":[100,196],"named":[101],"entity":[102],"recognition":[103],"(NER),":[104],"2)":[105],"provide":[106],"predictive":[108,138],"explainabilty":[109],"(interpretability)":[110,130],"framework":[111,131,195],"addresses":[113],"reasons":[115],"why":[116],"XL":[118],"may":[120,122],"or":[121,198,240],"not":[123,161],"have":[124],"bias,":[125],"3)":[126],"test":[127],"explainability":[129],"on":[132,152,204],"different":[133],"scenarios":[134],"evaluate":[136],"its":[137],"capabilities,":[139],"4)":[141],"consider":[142],"implications":[143],"of":[144,200,214,217,234],"any":[145],"insights":[146],"future":[148],"research":[149],"directions.":[150],"Based":[151],"experimental":[153],"results,":[154],"we":[155,191],"find":[156],"XLM-":[158],"R":[159],"significantly":[162,253],"biased":[163],"NER":[166,177,260],"task.":[167,267],"The":[168,268],"results":[169,269],"suggest":[170],"name":[172],"subwords":[174,218],"heavily":[175],"influence":[176],"performance":[178,233],"cross-lingual":[181],"transfer":[182],"reasonably":[185],"effective":[186],"models.":[189],"Finally,":[190],"discuss":[192],"general":[194],"debiasing":[197],"backdooring":[199],"based":[203],"subword":[205],"embedding":[206],"representations.":[207],"In":[208],"general,":[209],"knowing":[211],"values":[213],"embeddings":[216],"model,":[222],"one":[223],"select":[225],"triggers":[226],"(subwords)":[227],"will":[229],"impact":[230],"overall":[232],"task":[237,261],"either":[238],"positively":[239],"negatively.":[241],"such,":[243],"broad-use":[245],"backdoor":[246],"scheme":[247],"was":[248],"developed":[249],"tested":[251],"affects":[254],"recall":[256],"both":[258],"masked-based":[264],"sentiment":[265],"analysis":[266],"intriguing":[271],"promising.":[273]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2025-12-24T23:09:58.560324","created_date":"2025-10-10T00:00:00"}