{"id":"https://openalex.org/W4285211826","doi":"https://doi.org/10.1162/tacl_a_00472","title":"A Neighborhood Framework for Resource-Lean Content Flagging","display_name":"A Neighborhood Framework for Resource-Lean Content Flagging","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4285211826","doi":"https://doi.org/10.1162/tacl_a_00472"},"language":"en","primary_location":{"id":"doi:10.1162/tacl_a_00472","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00472","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00472/2020712/tacl_a_00472.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00472/2020712/tacl_a_00472.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089659476","display_name":"Sheikh Muhammad Sarwar","orcid":"https://orcid.org/0000-0003-4820-9201"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]},{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE","US"],"is_corresponding":true,"raw_author_name":"Sheikh Muhammad Sarwar","raw_affiliation_strings":["Amazon.com, US. smsarwar@amazon.com","University of Massachusetts, Amherst"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon.com, US. smsarwar@amazon.com","institution_ids":["https://openalex.org/I4210089985"]},{"raw_affiliation_string":"University of Massachusetts, Amherst","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043591543","display_name":"Dimitrina Zlatkova","orcid":"https://orcid.org/0009-0006-6766-4559"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Dimitrina Zlatkova","raw_affiliation_strings":["Checkstep, UK. didi@checkstep.com"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Checkstep, UK. didi@checkstep.com","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076120409","display_name":"Momchil Hardalov","orcid":"https://orcid.org/0000-0001-8095-3570"},"institutions":[{"id":"https://openalex.org/I58918642","display_name":"Sofia University \"St. Kliment Ohridski\"","ror":"https://ror.org/02jv3k292","country_code":"BG","type":"education","lineage":["https://openalex.org/I58918642"]}],"countries":["BG"],"is_corresponding":true,"raw_author_name":"Momchil Hardalov","raw_affiliation_strings":["Checkstep, UK. momchil@checkstep.com","Sofia University \u201cSt. Kliment Ohridski\u201d, Bulgaria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Checkstep, UK. momchil@checkstep.com","institution_ids":[]},{"raw_affiliation_string":"Sofia University \u201cSt. Kliment Ohridski\u201d, Bulgaria","institution_ids":["https://openalex.org/I58918642"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028121952","display_name":"Yoan Dinkov","orcid":"https://orcid.org/0009-0001-1415-8963"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yoan Dinkov","raw_affiliation_strings":["Checkstep, UK. yoan.dinkov@checkstep.com"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Checkstep, UK. yoan.dinkov@checkstep.com","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018976680","display_name":"Isabelle Augenstein","orcid":"https://orcid.org/0000-0003-1562-7909"},"institutions":[{"id":"https://openalex.org/I124055696","display_name":"University of Copenhagen","ror":"https://ror.org/035b05819","country_code":"DK","type":"education","lineage":["https://openalex.org/I124055696"]}],"countries":["DK"],"is_corresponding":true,"raw_author_name":"Isabelle Augenstein","raw_affiliation_strings":["Checkstep, UK. isabelle@checkstep.com","University of Copenhagen, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Checkstep, UK. isabelle@checkstep.com","institution_ids":[]},{"raw_affiliation_string":"University of Copenhagen, Denmark","institution_ids":["https://openalex.org/I124055696"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012055259","display_name":"Preslav Nakov","orcid":"https://orcid.org/0000-0002-3600-1510"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Preslav Nakov","raw_affiliation_strings":["Checkstep, UK. preslav.nakov@checkstep.com","Qatar Computing Research Institute, HBKU, Qatar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Checkstep, UK. preslav.nakov@checkstep.com","institution_ids":[]},{"raw_affiliation_string":"Qatar Computing Research Institute, HBKU, Qatar","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5012055259","https://openalex.org/A5018976680","https://openalex.org/A5028121952","https://openalex.org/A5043591543","https://openalex.org/A5076120409","https://openalex.org/A5089659476"],"corresponding_institution_ids":["https://openalex.org/I124055696","https://openalex.org/I24603500","https://openalex.org/I4210089985","https://openalex.org/I58918642"],"apc_list":null,"apc_paid":null,"fwci":0.9557,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.80103299,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"10","issue":null,"first_page":"484","last_page":"502"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13999","display_name":"Digital Rights Management and Security","score":0.986299991607666,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T13999","display_name":"Digital Rights Management and Security","score":0.986299991607666,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12335","display_name":"Sexuality, Behavior, and Technology","score":0.9370999932289124,"subfield":{"id":"https://openalex.org/subfields/3203","display_name":"Clinical Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/flagging","display_name":"Flagging","score":0.9831253886222839},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8449385166168213},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.6476162672042847},{"id":"https://openalex.org/keywords/content","display_name":"Content (measure theory)","score":0.44205591082572937},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.33543822169303894},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.06492871046066284}],"concepts":[{"id":"https://openalex.org/C2777548347","wikidata":"https://www.wikidata.org/wiki/Q5456937","display_name":"Flagging","level":2,"score":0.9831253886222839},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8449385166168213},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.6476162672042847},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.44205591082572937},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.33543822169303894},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.06492871046066284},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"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/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1162/tacl_a_00472","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00472","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00472/2020712/tacl_a_00472.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:553e7e2ed9104108abbffb68b0eadea4","is_oa":false,"landing_page_url":"https://doaj.org/article/553e7e2ed9104108abbffb68b0eadea4","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Transactions of the Association for Computational Linguistics, Vol 10 (2022)","raw_type":"article"},{"id":"pmh:oai:figshare.com:article/26889445","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"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":"","raw_type":"Text"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/3b36ed89-ab4d-4347-89c9-d75e80a7cf01","is_oa":true,"landing_page_url":"https://researchprofiles.ku.dk/da/publications/3b36ed89-ab4d-4347-89c9-d75e80a7cf01","pdf_url":null,"source":{"id":"https://openalex.org/S4306401983","display_name":"Research at the University of Copenhagen (University of Copenhagen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I124055696","host_organization_name":"University of Copenhagen","host_organization_lineage":["https://openalex.org/I124055696"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sarwar , S M , Zlatkova , D , Hardalov , M , Dinkov , Y , Augenstein , I & Nakov , P 2022 , ' A Neighborhood Framework for Resource-Lean Content Flagging ' , Transactions of the Association for Computational Linguistics , vol. 10 , pp. 484-502 . https://doi.org/10.1162/tacl_a_00472","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/tacl_a_00472","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00472","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00472/2020712/tacl_a_00472.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.699999988079071,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":75,"referenced_works":["https://openalex.org/W1583837637","https://openalex.org/W2049003051","https://openalex.org/W2098006457","https://openalex.org/W2153330999","https://openalex.org/W2536015822","https://openalex.org/W2540646130","https://openalex.org/W2563826943","https://openalex.org/W2602856279","https://openalex.org/W2740168486","https://openalex.org/W2742155240","https://openalex.org/W2747329762","https://openalex.org/W2750779823","https://openalex.org/W2760103715","https://openalex.org/W2885205901","https://openalex.org/W2886987881","https://openalex.org/W2914097099","https://openalex.org/W2934021436","https://openalex.org/W2952629768","https://openalex.org/W2954226438","https://openalex.org/W2954479967","https://openalex.org/W2954858824","https://openalex.org/W2962797668","https://openalex.org/W2962932155","https://openalex.org/W2962977603","https://openalex.org/W2963052389","https://openalex.org/W2963223515","https://openalex.org/W2963626623","https://openalex.org/W2963748066","https://openalex.org/W2969662548","https://openalex.org/W2970618241","https://openalex.org/W2970641574","https://openalex.org/W2971150411","https://openalex.org/W2972735048","https://openalex.org/W2972858693","https://openalex.org/W2973088264","https://openalex.org/W2973159684","https://openalex.org/W2978017171","https://openalex.org/W2988217457","https://openalex.org/W2990138404","https://openalex.org/W2997090102","https://openalex.org/W2998702515","https://openalex.org/W3011385529","https://openalex.org/W3023443524","https://openalex.org/W3035390927","https://openalex.org/W3100806282","https://openalex.org/W3100941475","https://openalex.org/W3102839769","https://openalex.org/W3104239954","https://openalex.org/W3114968871","https://openalex.org/W3115903740","https://openalex.org/W3133585485","https://openalex.org/W3134891661","https://openalex.org/W3173628907","https://openalex.org/W3174604160","https://openalex.org/W3177048205","https://openalex.org/W3186903869","https://openalex.org/W3199394329","https://openalex.org/W4299574851","https://openalex.org/W4404783772","https://openalex.org/W6632851186","https://openalex.org/W6732703391","https://openalex.org/W6735377749","https://openalex.org/W6755207826","https://openalex.org/W6760336251","https://openalex.org/W6767737316","https://openalex.org/W6768851824","https://openalex.org/W6770813465","https://openalex.org/W6773815586","https://openalex.org/W6777605459","https://openalex.org/W6777615688","https://openalex.org/W6779857854","https://openalex.org/W6779941907","https://openalex.org/W6783981339","https://openalex.org/W6791345680","https://openalex.org/W6793900221"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2807886874","https://openalex.org/W2946613364","https://openalex.org/W1697346018","https://openalex.org/W2113326855","https://openalex.org/W4393527151","https://openalex.org/W611259847","https://openalex.org/W2354785495"],"abstract_inverted_index":{"Abstract":[0],"We":[1,87],"propose":[2,88],"a":[3,31,36],"novel":[4],"framework":[5,27,55],"for":[6,113,142,154],"cross-":[7],"lingual":[8],"content":[9],"flagging":[10],"with":[11],"limited":[12],"target-":[13],"language":[14,61,115],"data,":[15],"which":[16],"significantly":[17],"outperforms":[18],"prior":[19,72],"work":[20,73],"in":[21,50,146],"terms":[22],"of":[23,39,120,140],"predictive":[24],"performance.":[25],"The":[26],"is":[28,35],"based":[29,82],"on":[30,74,83,106],"nearest-neighbor":[32],"architecture.":[33],"It":[34],"modern":[37],"instantiation":[38],"the":[40,64,79,143,147,155],"vanilla":[41],"k-nearest":[42],"neighbor":[43,85],"model,":[44],"as":[45],"we":[46,77,93,134],"use":[47],"Transformer":[48],"representations":[49],"all":[51],"its":[52],"components.":[53],"Our":[54,103],"can":[56],"adapt":[57],"to":[58,66,122],"new":[59],"source-":[60],"instances,":[62],"without":[63],"need":[65],"be":[67],"retrained":[68],"from":[69,109],"scratch.":[70],"Unlike":[71],"neighborhood-based":[75],"approaches,":[76],"encode":[78],"neighborhood":[80],"information":[81],"query\u2013":[84],"interactions.":[86],"two":[89,110],"encoding":[90],"schemes":[91],"and":[92,100,151],"show":[94,117],"their":[95],"effectiveness":[96],"using":[97],"both":[98],"qualitative":[99],"quantitative":[101],"analysis.":[102],"evaluation":[104],"results":[105],"eight":[107],"languages":[108,145],"different":[111],"datasets":[112],"abusive":[114],"detection":[116],"sizable":[118],"improvements":[119],"up":[121],"9.5":[123],"F1":[124,138],"points":[125,139,153],"absolute":[126,137],"(for":[127],"Italian)":[128],"over":[129],"strong":[130],"baselines.":[131],"On":[132],"average,":[133],"achieve":[135],"3.6":[136],"improvement":[141],"three":[144],"Jigsaw":[148],"Multilingual":[149],"dataset":[150],"2.14":[152],"WUL":[156],"dataset.":[157]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}