{"id":"https://openalex.org/W4321351392","doi":"https://doi.org/10.1007/s10579-023-09637-4","title":"Label modification and bootstrapping for zero-shot cross-lingual hate speech detection","display_name":"Label modification and bootstrapping for zero-shot cross-lingual hate speech detection","publication_year":2023,"publication_date":"2023-02-18","ids":{"openalex":"https://openalex.org/W4321351392","doi":"https://doi.org/10.1007/s10579-023-09637-4","pmid":"https://pubmed.ncbi.nlm.nih.gov/38021031"},"language":"en","primary_location":{"id":"doi:10.1007/s10579-023-09637-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10579-023-09637-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10579-023-09637-4.pdf","source":{"id":"https://openalex.org/S4306424877","display_name":"Language Resources and Evaluation","issn_l":"1574-020X","issn":["1574-020X","1574-0218"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Language Resources and Evaluation","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10579-023-09637-4.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081295642","display_name":"Irina Bigoulaeva","orcid":"https://orcid.org/0000-0002-6955-981X"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Irina Bigoulaeva","raw_affiliation_strings":["Ubiquitous Knowledge Processing Lab (UKP Lab), Department of Computer Science, Technical University of Darmstadt, Darmstadt, Germany"],"raw_orcid":"https://orcid.org/0000-0002-6955-981X","affiliations":[{"raw_affiliation_string":"Ubiquitous Knowledge Processing Lab (UKP Lab), Department of Computer Science, Technical University of Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090950630","display_name":"Viktor Hangya","orcid":"https://orcid.org/0000-0002-5144-3069"},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Viktor Hangya","raw_affiliation_strings":["Center for Information and Language Processing, LMU Munich, Munich, Germany"],"raw_orcid":"https://orcid.org/0000-0002-5144-3069","affiliations":[{"raw_affiliation_string":"Center for Information and Language Processing, LMU Munich, Munich, Germany","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027450194","display_name":"Iryna Gurevych","orcid":"https://orcid.org/0000-0003-2187-7621"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Iryna Gurevych","raw_affiliation_strings":["Ubiquitous Knowledge Processing Lab (UKP Lab), Department of Computer Science, Technical University of Darmstadt, Darmstadt, Germany"],"raw_orcid":"https://orcid.org/0000-0003-2187-7621","affiliations":[{"raw_affiliation_string":"Ubiquitous Knowledge Processing Lab (UKP Lab), Department of Computer Science, Technical University of Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101957153","display_name":"Alexander Fraser","orcid":"https://orcid.org/0000-0003-4891-682X"},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alexander Fraser","raw_affiliation_strings":["Center for Information and Language Processing, LMU Munich, Munich, Germany"],"raw_orcid":"https://orcid.org/0000-0003-4891-682X","affiliations":[{"raw_affiliation_string":"Center for Information and Language Processing, LMU Munich, Munich, Germany","institution_ids":["https://openalex.org/I8204097"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5081295642"],"corresponding_institution_ids":["https://openalex.org/I31512782"],"apc_list":{"value":3090,"currency":"USD","value_usd":3090},"apc_paid":{"value":3090,"currency":"USD","value_usd":3090},"fwci":2.3957,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":{"value":0.89758858,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"57","issue":"4","first_page":"1515","last_page":"1546"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9998999834060669,"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/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9998999834060669,"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/T11598","display_name":"Internet Traffic Analysis and Secure E-voting","score":0.9002000093460083,"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":0.7965689301490784},{"id":"https://openalex.org/keywords/bootstrapping","display_name":"Bootstrapping (finance)","score":0.704818069934845},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6828627586364746},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5672351121902466},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5458061099052429},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5288551449775696},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5116193890571594},{"id":"https://openalex.org/keywords/undersampling","display_name":"Undersampling","score":0.47512298822402954},{"id":"https://openalex.org/keywords/oversampling","display_name":"Oversampling","score":0.4445287585258484},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4356077313423157},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.43439194560050964},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.42619216442108154},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.41486111283302307},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3815784454345703},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3219638466835022}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7965689301490784},{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.704818069934845},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6828627586364746},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5672351121902466},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5458061099052429},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5288551449775696},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5116193890571594},{"id":"https://openalex.org/C136536468","wikidata":"https://www.wikidata.org/wiki/Q1225894","display_name":"Undersampling","level":2,"score":0.47512298822402954},{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.4445287585258484},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4356077313423157},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.43439194560050964},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.42619216442108154},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.41486111283302307},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3815784454345703},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3219638466835022},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C106159729","wikidata":"https://www.wikidata.org/wiki/Q2294553","display_name":"Financial economics","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},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1007/s10579-023-09637-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10579-023-09637-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10579-023-09637-4.pdf","source":{"id":"https://openalex.org/S4306424877","display_name":"Language Resources and Evaluation","issn_l":"1574-020X","issn":["1574-020X","1574-0218"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Language Resources and Evaluation","raw_type":"journal-article"},{"id":"pmid:38021031","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38021031","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Language resources and evaluation","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:10656307","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10656307","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10656307/pdf/10579_2023_Article_9637.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Lang Resour Eval","raw_type":"Text"},{"id":"pmh:oai:tubiblio.ulb.tu-darmstadt.de:136782","is_oa":false,"landing_page_url":"http://tubiblio.ulb.tu-darmstadt.de/136782/","pdf_url":null,"source":{"id":"https://openalex.org/S4377196390","display_name":"TUbilio (Technical University of Darmstadt)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I31512782","host_organization_name":"Technische Universit\u00e4t Darmstadt","host_organization_lineage":["https://openalex.org/I31512782"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Artikel"}],"best_oa_location":{"id":"doi:10.1007/s10579-023-09637-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10579-023-09637-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10579-023-09637-4.pdf","source":{"id":"https://openalex.org/S4306424877","display_name":"Language Resources and Evaluation","issn_l":"1574-020X","issn":["1574-020X","1574-0218"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Language Resources and Evaluation","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.4300000071525574,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G2893748681","display_name":null,"funder_award_id":"640550","funder_id":"https://openalex.org/F4320334678","funder_display_name":"European Research Council"},{"id":"https://openalex.org/G7600267275","display_name":null,"funder_award_id":"FR 2829/4-1","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320323384","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24"},{"id":"https://openalex.org/F4320334678","display_name":"European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4321351392.pdf"},"referenced_works_count":61,"referenced_works":["https://openalex.org/W1614298861","https://openalex.org/W1832693441","https://openalex.org/W2124807415","https://openalex.org/W2126725946","https://openalex.org/W2148143831","https://openalex.org/W2154582566","https://openalex.org/W2473555522","https://openalex.org/W2493916176","https://openalex.org/W2509254371","https://openalex.org/W2540646130","https://openalex.org/W2595653137","https://openalex.org/W2596638843","https://openalex.org/W2599674900","https://openalex.org/W2740168486","https://openalex.org/W2765906452","https://openalex.org/W2790839522","https://openalex.org/W2798908575","https://openalex.org/W2800225499","https://openalex.org/W2887782043","https://openalex.org/W2889016530","https://openalex.org/W2892181857","https://openalex.org/W2900160274","https://openalex.org/W2900796872","https://openalex.org/W2912102236","https://openalex.org/W2914740698","https://openalex.org/W2914827868","https://openalex.org/W2916719435","https://openalex.org/W2936503027","https://openalex.org/W2941596569","https://openalex.org/W2954226438","https://openalex.org/W2954793188","https://openalex.org/W2956090150","https://openalex.org/W2963532322","https://openalex.org/W2963943967","https://openalex.org/W2969662548","https://openalex.org/W2991020115","https://openalex.org/W3013027210","https://openalex.org/W3014487746","https://openalex.org/W3023443524","https://openalex.org/W3030681628","https://openalex.org/W3091315987","https://openalex.org/W3100140585","https://openalex.org/W3100941475","https://openalex.org/W3104209339","https://openalex.org/W3109275892","https://openalex.org/W3115903740","https://openalex.org/W3135855479","https://openalex.org/W3155025376","https://openalex.org/W3155638757","https://openalex.org/W3174882277","https://openalex.org/W3184133963","https://openalex.org/W3189422672","https://openalex.org/W3197986154","https://openalex.org/W4214616937","https://openalex.org/W4224278554","https://openalex.org/W4242076805","https://openalex.org/W4244396790","https://openalex.org/W4248491679","https://openalex.org/W4299579390","https://openalex.org/W4312527798","https://openalex.org/W6744957266"],"related_works":["https://openalex.org/W4308469503","https://openalex.org/W32988189","https://openalex.org/W2904737874","https://openalex.org/W2399571531","https://openalex.org/W80466363","https://openalex.org/W4288337828","https://openalex.org/W2947132063","https://openalex.org/W4287816717","https://openalex.org/W3016117175","https://openalex.org/W3199294801"],"abstract_inverted_index":{"The":[0],"goal":[1],"of":[2,16,25,46,95,106,160,169,180],"hate":[3,38,52,77,99,173,185],"speech":[4,39,53,78,100,174],"detection":[5,40,79],"is":[6,30],"to":[7,19,32,60,75,114,127,184,189],"filter":[8],"negative":[9],"online":[10],"content":[11],"aiming":[12],"at":[13],"certain":[14],"groups":[15],"people.":[17],"Due":[18],"the":[20,49,104,121,128,167,177],"easy":[21],"accessibility":[22],"and":[23,124,135,198,201],"multilinguality":[24],"social":[26],"media":[27],"platforms,":[28],"it":[29,58],"crucial":[31],"protect":[33],"everyone":[34],"which":[35,102,131],"requires":[36],"building":[37],"systems":[41,62,119],"for":[42,63,150],"a":[43],"wide":[44],"range":[45],"languages.":[47,65],"However,":[48],"available":[50],"labeled":[51,133],"datasets":[54],"are":[55],"limited,":[56],"making":[57],"difficult":[59],"build":[61],"many":[64],"In":[66],"this":[67],"paper":[68],"we":[69,165],"focus":[70],"on":[71,120],"cross-lingual":[72,111],"transfer":[73],"learning":[74],"support":[76],"in":[80,172],"low-resource":[81],"languages,":[82],"while":[83],"highlighting":[84],"label":[85,93,170],"issues":[86],"across":[87],"application":[88,105],"scenarios,":[89],"such":[90,107],"as":[91],"inconsistent":[92],"sets":[94],"corpora":[96],"or":[97],"differing":[98],"definitions,":[101],"hinder":[103],"methods.":[108],"We":[109,143,193],"leverage":[110],"word":[112],"embeddings":[113],"train":[115],"our":[116],"neural":[117],"network":[118],"source":[122],"language":[123,148],"apply":[125],"them":[126],"target":[129,147],"language,":[130],"lacks":[132],"examples,":[134],"show":[136,202],"that":[137],"good":[138],"performance":[139],"can":[140],"be":[141],"achieved.":[142],"then":[144],"incorporate":[145],"unlabeled":[146],"data":[149,196],"further":[151],"model":[152,162,191],"improvements":[153],"by":[154],"bootstrapping":[155],"labels":[156],"using":[157],"an":[158],"ensemble":[159],"different":[161],"architectures.":[163],"Furthermore,":[164],"investigate":[166],"issue":[168],"imbalance":[171],"datasets,":[175],"since":[176],"high":[178],"ratio":[179],"non-hate":[181],"examples":[182,186],"compared":[183],"often":[187],"leads":[188],"low":[190],"performance.":[192],"test":[194],"simple":[195],"undersampling":[197],"oversampling":[199],"techniques":[200],"their":[203],"effectiveness.":[204]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}
