{"id":"https://openalex.org/W3202133432","doi":"https://doi.org/10.1145/3544104","title":"Generalized Funnelling: Ensemble Learning and Heterogeneous Document Embeddings for Cross-Lingual Text Classification","display_name":"Generalized Funnelling: Ensemble Learning and Heterogeneous Document Embeddings for Cross-Lingual Text Classification","publication_year":2022,"publication_date":"2022-06-13","ids":{"openalex":"https://openalex.org/W3202133432","doi":"https://doi.org/10.1145/3544104","mag":"3202133432"},"language":"en","primary_location":{"id":"doi:10.1145/3544104","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3544104","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3544104","source":{"id":"https://openalex.org/S4394735545","display_name":"ACM Transactions on Information Systems","issn_l":"1046-8188","issn":["1046-8188","1558-2868"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Information Systems","raw_type":"journal-article"},"type":"book-chapter","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3544104","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086354805","display_name":"Alejandro Moreo","orcid":"https://orcid.org/0000-0002-0377-1025"},"institutions":[{"id":"https://openalex.org/I4210107558","display_name":"Consorzio Pisa Ricerche","ror":"https://ror.org/01t0n3b84","country_code":"IT","type":"facility","lineage":["https://openalex.org/I4210107558"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alejandro Moreo","raw_affiliation_strings":["Consiglio Nazionale delle Ricerche, Pisa, Italy"],"raw_orcid":"https://orcid.org/0000-0002-0377-1025","affiliations":[{"raw_affiliation_string":"Consiglio Nazionale delle Ricerche, Pisa, Italy","institution_ids":["https://openalex.org/I4210107558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001908458","display_name":"Andrea Pedrotti","orcid":"https://orcid.org/0000-0002-2322-7043"},"institutions":[{"id":"https://openalex.org/I4210107558","display_name":"Consorzio Pisa Ricerche","ror":"https://ror.org/01t0n3b84","country_code":"IT","type":"facility","lineage":["https://openalex.org/I4210107558"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Andrea Pedrotti","raw_affiliation_strings":["Consiglio Nazionale delle Ricerche, Pisa, Italy"],"raw_orcid":"https://orcid.org/0000-0002-2322-7043","affiliations":[{"raw_affiliation_string":"Consiglio Nazionale delle Ricerche, Pisa, Italy","institution_ids":["https://openalex.org/I4210107558"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063975186","display_name":"Fabrizio Sebastiani","orcid":"https://orcid.org/0000-0003-4221-6427"},"institutions":[{"id":"https://openalex.org/I4210107558","display_name":"Consorzio Pisa Ricerche","ror":"https://ror.org/01t0n3b84","country_code":"IT","type":"facility","lineage":["https://openalex.org/I4210107558"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Fabrizio Sebastiani","raw_affiliation_strings":["Consiglio Nazionale delle Ricerche, Pisa, Italy"],"raw_orcid":"https://orcid.org/0000-0003-4221-6427","affiliations":[{"raw_affiliation_string":"Consiglio Nazionale delle Ricerche, Pisa, Italy","institution_ids":["https://openalex.org/I4210107558"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00532004,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"41","issue":"2","first_page":"1","last_page":"37"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9980999827384949,"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":0.9980999827384949,"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":0.9970999956130981,"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"}},{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9925000071525574,"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/word","display_name":"Word (group theory)","score":0.6540769338607788},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5944390296936035},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5885834097862244},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5806773900985718},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5678586959838867},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5543771386146545},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"Ensemble learning","score":0.5456904768943787},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5102789402008057},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.4651537835597992},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4398387670516968},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.29125386476516724},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.09330946207046509}],"concepts":[{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6540769338607788},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5944390296936035},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5885834097862244},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5806773900985718},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5678586959838867},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5543771386146545},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.5456904768943787},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5102789402008057},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.4651537835597992},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4398387670516968},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.29125386476516724},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.09330946207046509},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1145/3544104","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3544104","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3544104","source":{"id":"https://openalex.org/S4394735545","display_name":"ACM Transactions on Information Systems","issn_l":"1046-8188","issn":["1046-8188","1558-2868"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Information Systems","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2110.14764","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2110.14764","pdf_url":"https://arxiv.org/pdf/2110.14764","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"pmh:oai:zenodo.org:7090083","is_oa":true,"landing_page_url":"https://zenodo.org/record/7090083","pdf_url":"https://zenodo.org/record/7090083","source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"ACM Transactions on Information Systems","raw_type":"info:eu-repo/semantics/article"},{"id":"doi:10.48550/arxiv.2110.14764","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2110.14764","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"mag:3202133432","is_oa":false,"landing_page_url":"http://ceur-ws.org/Vol-2947/paper28.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306472698","display_name":"IIR eBooks","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":"ebook platform"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"IIR eBooks","raw_type":null}],"best_oa_location":{"id":"doi:10.1145/3544104","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3544104","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3544104","source":{"id":"https://openalex.org/S4394735545","display_name":"ACM Transactions on Information Systems","issn_l":"1046-8188","issn":["1046-8188","1558-2868"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Information Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.41999998688697815,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"},{"score":0.4000000059604645,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1322071649","display_name":null,"funder_award_id":"951911","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G3542563520","display_name":null,"funder_award_id":"ICT-48-2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G3561142481","display_name":null,"funder_award_id":"823914","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"},{"id":"https://openalex.org/G4397263494","display_name":null,"funder_award_id":"951911","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"},{"id":"https://openalex.org/G4937468798","display_name":null,"funder_award_id":"H2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G5871011076","display_name":null,"funder_award_id":"ICT-48-2020","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"},{"id":"https://openalex.org/G8043423149","display_name":null,"funder_award_id":"823914, 871042 and 951911","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8274803949","display_name":null,"funder_award_id":"871042","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8296550949","display_name":null,"funder_award_id":"823914","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G899169222","display_name":null,"funder_award_id":"871042","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3202133432.pdf","grobid_xml":"https://content.openalex.org/works/W3202133432.grobid-xml"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W342285082","https://openalex.org/W1489959797","https://openalex.org/W1615991656","https://openalex.org/W1983578042","https://openalex.org/W1994500780","https://openalex.org/W2014364160","https://openalex.org/W2033436836","https://openalex.org/W2033593667","https://openalex.org/W2064675550","https://openalex.org/W2130903752","https://openalex.org/W2147152072","https://openalex.org/W2149201576","https://openalex.org/W2157331557","https://openalex.org/W2250539671","https://openalex.org/W2287612586","https://openalex.org/W2294774419","https://openalex.org/W2301772290","https://openalex.org/W2462891382","https://openalex.org/W2507974895","https://openalex.org/W2548695521","https://openalex.org/W2549102774","https://openalex.org/W2561995736","https://openalex.org/W2741602058","https://openalex.org/W2758375579","https://openalex.org/W2769280657","https://openalex.org/W2911379778","https://openalex.org/W2916332638","https://openalex.org/W2920277907","https://openalex.org/W2952289666","https://openalex.org/W2962739339","https://openalex.org/W2963341956","https://openalex.org/W2963912736","https://openalex.org/W2963967134","https://openalex.org/W2970193165","https://openalex.org/W2979826702","https://openalex.org/W2998704965","https://openalex.org/W3035032094","https://openalex.org/W3103065189","https://openalex.org/W3105973526","https://openalex.org/W3114725666","https://openalex.org/W3129401410","https://openalex.org/W3156038928","https://openalex.org/W3157279044","https://openalex.org/W3176109448","https://openalex.org/W4230987693","https://openalex.org/W4236119072","https://openalex.org/W6688325169"],"related_works":["https://openalex.org/W3157279044","https://openalex.org/W2963967134","https://openalex.org/W3127869043","https://openalex.org/W3113232787","https://openalex.org/W1951455856","https://openalex.org/W2591546050","https://openalex.org/W2805887137","https://openalex.org/W2891578174","https://openalex.org/W2964751504","https://openalex.org/W3037862427","https://openalex.org/W2963912736","https://openalex.org/W2919466488","https://openalex.org/W2340588715","https://openalex.org/W3124750518","https://openalex.org/W2953207455","https://openalex.org/W2962948877","https://openalex.org/W2766034339","https://openalex.org/W3142516437","https://openalex.org/W3103038538","https://openalex.org/W2090708902"],"abstract_inverted_index":{"Funnelling":[0,107],"(":[1,108],"Fun":[2,86,114,165,218],")":[3,166],"is":[4,61,243],"a":[5,16,34,41,64,111,136,157],"recently":[6],"proposed":[7],"method":[8],"for":[9,20,50,53,233],"cross-lingual":[10],"text":[11,236],"classification":[12,59],"(CLTC)":[13],"based":[14],"on":[15,33,228],"two-tier":[17],"learning":[18,23],"ensemble":[19,27],"heterogeneous":[21],"transfer":[22],"(HTL).":[24],"In":[25,101],"this":[26,68,81,102,211],"method,":[28],"1st-tier":[29,122],"classifiers,":[30],"each":[31,51,54,134],"working":[32],"different":[35],"and":[36,56,80,199,219],"language-dependent":[37,131],"feature":[38],"space,":[39],"return":[40],"vector":[42,69,158],"of":[43,113,116,140,148,159,176,213],"calibrated":[44,160],"posterior":[45,161],"probabilities":[46,162],"(with":[47],"one":[48],"dimension":[49],"class)":[52],"document,":[55],"the":[57,141,152],"final":[58],"decision":[60],"taken":[62],"by":[63,184,192,204,223],"meta-classifier":[65,74,153],"that":[66,133,172,210,240],"uses":[67],"as":[70,155,179],"its":[71],"input.":[72],"The":[73],"can":[75,124],"thus":[76],"exploit":[77],"class-class":[78],"correlations,":[79,177],"(among":[82],"other":[83,169,174],"things)":[84],"gives":[85],"an":[87,117,146],"edge":[88],"over":[89,217,220],"CLTC":[90],"systems":[91],"in":[92,120,150,164],"which":[93,121,151],"these":[94],"correlations":[95,181,189,201],"cannot":[96],"be":[97,125],"brought":[98],"to":[99,168],"bear.":[100],"article,":[103],"we":[104],"describe":[105,145],"Generalized":[106],"gFun":[109,149,214,242],"),":[110,187,198],"generalization":[112],"consisting":[115],"HTL":[118],"architecture":[119],"components":[123],"arbitrary":[126],"view-generating":[127],"functions":[128,132],",":[129],"i.e.,":[130],"produce":[135],"language-independent":[137],"representation":[138],"(\u201cview\u201d)":[139],"(monolingual)":[142],"document.":[143],"We":[144,208],"instance":[147,212],"receives":[154],"input":[156],"(as":[163,182,190,202],"aggregated":[167],"embedded":[170],"representations":[171],"embody":[173],"types":[175],"such":[178],"word-class":[180],"encoded":[183,191,203],"Word-Class":[185],"Embeddings":[186,197],"word-word":[188],"Multilingual":[193],"Unsupervised":[194],"or":[195],"Supervised":[196],"word-context":[200],"multilingual":[205,234],"BERT":[206],").":[207],"show":[209],"substantially":[215],"improves":[216],"state-of-the-art":[221],"baselines":[222],"reporting":[224],"experimental":[225],"results":[226],"obtained":[227],"two":[229],"large,":[230],"standard":[231],"datasets":[232],"multilabel":[235],"classification.":[237],"Our":[238],"code":[239],"implements":[241],"publicly":[244],"available.":[245]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}