{"id":"https://openalex.org/W7140090461","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.349","title":"Active Learning with Non-Uniform Costs for African Natural Language Processing","display_name":"Active Learning with Non-Uniform Costs for African Natural Language Processing","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140090461","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.349"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-eacl.349","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.349","pdf_url":"https://aclanthology.org/2026.findings-eacl.349.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-eacl.349.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058219704","display_name":"Bonaventure F. P. Dossou","orcid":"https://orcid.org/0000-0002-0519-1761"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bonaventure F. P. Dossou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130388085","display_name":"Ines Arous","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ines Arous","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130333239","display_name":"Audrey Durand","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Audrey Durand","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Jackie Chi Kit Cheung","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jackie Chi Kit Cheung","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6644","last_page":"6656"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.7906000018119812,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.7906000018119812,"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/T13194","display_name":"ICT in Developing Communities","score":0.016699999570846558,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.014000000432133675,"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/active-learning","display_name":"Active learning (machine learning)","score":0.5516999959945679},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.43369999527931213},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.3467000126838684},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.3059999942779541},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2549000084400177}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5758000016212463},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.5516999959945679},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43689998984336853},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.43369999527931213},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39590001106262207},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.3467000126838684},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.31040000915527344},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3059999942779541},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2549000084400177},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.25209999084472656},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-eacl.349","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.349","pdf_url":"https://aclanthology.org/2026.findings-eacl.349.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-eacl.349","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.349","pdf_url":"https://aclanthology.org/2026.findings-eacl.349.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7689051032066345,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320309949","display_name":"Canadian Institute for Advanced Research","ror":"https://ror.org/01sdtdd95"},{"id":"https://openalex.org/F4320326644","display_name":"Canada First Research Excellence Fund","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140090461.pdf","grobid_xml":"https://content.openalex.org/works/W7140090461.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Labeling":[0],"datasets":[1],"for":[2,152],"African":[3,93,159],"languages":[4],"poses":[5],"substantial":[6],"challenges":[7],"due":[8],"to":[9,19,74],"the":[10,64,83,131],"diverse":[11],"settings":[12],"in":[13,47,135,158],"which":[14,43],"annotations":[15],"are":[16,145],"collected,":[17],"leading":[18],"highly":[20],"variable":[21],"labeling":[22],"costs.These":[23],"costs":[24,144],"vary":[25],"with":[26,68],"task":[27],"complexity,":[28],"annotator":[29],"expertise,":[30],"and":[31,77,106,113,162],"data":[32],"availability.Yet":[33],"most":[34],"active":[35,59,100,154],"learning":[36,60,101],"(AL)":[37],"frameworks":[38],"assume":[39],"uniform":[40],"annotation":[41,124,143],"costs,":[42],"limits":[44],"their":[45],"applicability":[46],"real-world,":[48],"resource-constrained":[49],"scenarios.To":[50],"address":[51],"this,":[52],"we":[53],"introduce":[54],"KnapsackBALD,":[55],"a":[56,69,86],"novel":[57],"cost-aware":[58],"method":[61,95],"that":[62,141],"integrates":[63],"BatchBALD":[65],"acquisition":[66,149],"strategy":[67],"0-1":[70],"Knapsack":[71],"optimization":[72],"objective":[73],"select":[75],"informative":[76],"budget-efficient":[78],"samples.We":[79],"evaluate":[80],"KnapsackBALD":[81,134],"on":[82],"MasakhaNEWS":[84],"dataset,":[85],"multilingual":[87],"news":[88],"classification":[89],"benchmark":[90],"covering":[91],"11":[92],"languages.Our":[94],"consistently":[96],"outperforms":[97],"seven":[98],"strong":[99],"baselines,":[102],"including":[103],"BALD,":[104],"BatchBALD,":[105],"stochastic":[107],"sampling":[108],"variants":[109],"such":[110],"as":[111,123,156],"PowerBALD":[112],"Softmax-BALD,":[114],"across":[115],"all":[116],"three":[117],"cost":[118,125,137],"scenarios.The":[119],"performance":[120],"gap":[121],"widens":[122],"imbalances":[126],"become":[127],"more":[128],"extreme,":[129],"demonstrating":[130],"robustness":[132],"of":[133],"different":[136],"settings.These":[138],"findings":[139],"show":[140],"when":[142],"explicitly":[146],"heterogeneous,":[147],"cost-sensitive":[148],"is":[150,167],"critical":[151],"effective":[153],"learning,":[155],"demonstrated":[157],"Languages":[160],"NLP":[161],"similar":[163],"settings.Our":[164],"code":[165],"base":[166],"open-sourced":[168],"here.":[169]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-24T00:00:00"}