{"id":"https://openalex.org/W4416034429","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1359","title":"Active Learning for Multidialectal Arabic POS Tagging","display_name":"Active Learning for Multidialectal Arabic POS Tagging","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034429","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1359"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1359","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1359","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1359.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: EMNLP 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.1359.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046284249","display_name":"Diyam Akra","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Diyam Akra","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031419933","display_name":"Mohammed Khalilia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mohammed Khalilia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5050418400","display_name":"Mustafa Jarrar","orcid":"https://orcid.org/0000-0003-4351-4207"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mustafa Jarrar","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":"24960","last_page":"24973"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.3492000102996826,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.3492000102996826,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.3422999978065491,"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/T11587","display_name":"Second Language Acquisition and Learning","score":0.05490000173449516,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational 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/active-learning","display_name":"Active learning (machine learning)","score":0.5116000175476074},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.35830000042915344},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.27480000257492065},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.26809999346733093},{"id":"https://openalex.org/keywords/statistical-learning","display_name":"Statistical learning","score":0.23190000653266907}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6201000213623047},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.590399980545044},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5631999969482422},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.5116000175476074},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.35830000042915344},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3310000002384186},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C2982736386","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Statistical learning","level":2,"score":0.23190000653266907},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.22869999706745148}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.1359","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1359","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1359.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: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1359","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1359","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1359.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: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034429.pdf","grobid_xml":"https://content.openalex.org/works/W4416034429.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multidialectal":[0],"Arabic":[1,71],"POS":[2,16,72],"tagging":[3,17],"is":[4,82],"challenging":[5],"due":[6],"to":[7,23,97],"the":[8,24,38,59,99,109,145],"morphological":[9],"richness":[10],"and":[11,36,124],"high":[12,85],"variability":[13],"among":[14],"dialects.While":[15],"for":[18,32,69,84],"MSA":[19],"has":[20],"advanced":[21],"thanks":[22],"availability":[25],"of":[26,40,101,133,142],"annotated":[27,41,136],"datasets,":[28],"creating":[29],"similar":[30],"resources":[31],"dialects":[33],"remains":[34],"costly":[35],"laborintensive.Increasing":[37],"size":[39],"datasets":[42],"does":[43],"not":[44],"necessarily":[45],"result":[46],"in":[47],"better":[48],"performance.Active":[49],"learning":[50,67,122],"offers":[51],"a":[52,91],"more":[53],"efficient":[54],"alternative":[55],"by":[56,112],"prioritizing":[57],"annotating":[58,77],"most":[60],"informative":[61],"samples.This":[62],"paper":[63],"proposes":[64],"an":[65,120,140],"active":[66,121],"approach":[68],"multidialectal":[70],"tagging.Our":[73],"experiments":[74],"revealed":[75],"that":[76,89],"approximately":[78],"15,":[79],"000":[80,115,135],"tokens":[81],"sufficient":[83],"performance.We":[86],"further":[87],"demonstrate":[88,125],"using":[90],"fine-tuned":[92],"model":[93],"from":[94,104],"one":[95],"dialect":[96,106],"guide":[98],"selection":[100],"initial":[102],"samples":[103],"another":[105],"accelerates":[107],"convergence-reducing":[108],"annotation":[110],"requirement":[111],"about":[113],"2,":[114],"tokens.In":[116],"conclusion,":[117],"we":[118],"propose":[119],"pipeline":[123],"that,":[126],"upon":[127],"reaching":[128],"its":[129],"defined":[130],"stopping":[131],"point":[132],"16,":[134],"tokens,":[137],"it":[138],"achieves":[139],"accuracy":[141],"97.6%":[143],"on":[144],"Emirati":[146],"Corpus.":[147]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-08T00:00:00"}