{"id":"https://openalex.org/W4416037622","doi":"https://doi.org/10.18653/v1/2025.arabicnlp-sharedtasks.81","title":"TranTranUIT at MAHED Shared Task: Multilingual Transformer Ensemble with Advanced Data Augmentation and Optuna-based Hyperparameter Optimization","display_name":"TranTranUIT at MAHED Shared Task: Multilingual Transformer Ensemble with Advanced Data Augmentation and Optuna-based Hyperparameter Optimization","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416037622","doi":"https://doi.org/10.18653/v1/2025.arabicnlp-sharedtasks.81"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.arabicnlp-sharedtasks.81","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.arabicnlp-sharedtasks.81","pdf_url":"https://aclanthology.org/2025.arabicnlp-sharedtasks.81.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":"Proceedings of The Third Arabic Natural Language Processing Conference: Shared Tasks","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.arabicnlp-sharedtasks.81.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Trinh Tran Tran","orcid":null},"institutions":[{"id":"https://openalex.org/I123565023","display_name":"Vietnam National University Ho Chi Minh City","ror":"https://ror.org/00waaqh38","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Trinh Tran Tran","raw_affiliation_strings":["University of Information Technology-VNUHCM , Vietnam National University , Ho Chi Minh City , Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Information Technology-VNUHCM , Vietnam National University , Ho Chi Minh City , Vietnam","institution_ids":["https://openalex.org/I123565023"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047610312","display_name":"Th\u00ecn \u0110\u1eb7ng V\u0103n","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Th\u00ecn \u0110\u1eb7ng V\u0103n","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.15997614,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"603","last_page":"607"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.07620000094175339,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.07620000094175339,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.07559999823570251,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.06310000270605087,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/hyperparameter","display_name":"Hyperparameter","score":0.5685999989509583},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4453999996185303},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"Ensemble learning","score":0.35690000653266907},{"id":"https://openalex.org/keywords/hyperparameter-optimization","display_name":"Hyperparameter optimization","score":0.32330000400543213},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3003000020980835},{"id":"https://openalex.org/keywords/spurious-relationship","display_name":"Spurious relationship","score":0.28999999165534973}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6887000203132629},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5799999833106995},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.5685999989509583},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4722999930381775},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4453999996185303},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.35690000653266907},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3382999897003174},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32739999890327454},{"id":"https://openalex.org/C10485038","wikidata":"https://www.wikidata.org/wiki/Q48996162","display_name":"Hyperparameter optimization","level":3,"score":0.32330000400543213},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3003000020980835},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.28999999165534973},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.27570000290870667},{"id":"https://openalex.org/C3020493868","wikidata":"https://www.wikidata.org/wiki/Q55631277","display_name":"Real world data","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.arabicnlp-sharedtasks.81","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.arabicnlp-sharedtasks.81","pdf_url":"https://aclanthology.org/2025.arabicnlp-sharedtasks.81.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":"Proceedings of The Third Arabic Natural Language Processing Conference: Shared Tasks","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.arabicnlp-sharedtasks.81","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.arabicnlp-sharedtasks.81","pdf_url":"https://aclanthology.org/2025.arabicnlp-sharedtasks.81.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":"Proceedings of The Third Arabic Natural Language Processing Conference: Shared Tasks","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416037622.pdf","grobid_xml":"https://content.openalex.org/works/W4416037622.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Detecting":[0],"hate":[1,156],"and":[2,30,48,56,71,121,129,150,157],"hope":[3,158],"speech":[4,159],"in":[5,13,34,154],"Arabic":[6,131,155],"social":[7],"media":[8],"remains":[9],"a":[10,38,50,63,104],"critical":[11],"challenge":[12],"the":[14,25,110,115],"MAHED":[15],"2025":[16],"Shared":[17],"Task":[18],"(Zaghouani":[19],"et":[20,87,95],"al.,":[21,88,96],"2025)":[22],"due":[23],"to":[24,81,98],"complex":[26],"diglossia,":[27],"diverse":[28],"dialects,":[29],"prevalent":[31],"orthographic":[32],"noise":[33,79],"usergenerated":[35],"texts.We":[36],"introduce":[37],"multilingual":[39,124],"transformer":[40],"ensemble":[41],"that":[42,137],"integrates":[43],"three":[44],"complementary":[45,139],"encoders-AraBERTv2,":[46],"AraBERT-Twitter,":[47],"XLM-RoBERTa-using":[49],"uniform":[51],"soft":[52],"voting":[53],"approach":[54],"(Salur":[55],"Aydn,":[57],"2022).Each":[58],"model":[59,118],"is":[60],"fine-tuned":[61],"with":[62,142],"balanced":[64],"data":[65],"augmentation":[66,144],"strategy,":[67],"combining":[68,138],"70%":[69],"backtranslation":[70],"30%":[72],"Easy":[73],"Data":[74],"Augmentation":[75],"(EDA),":[76],"followed":[77],"by":[78,119],"induction":[80],"mimic":[82],"real-world":[83],"textual":[84],"perturbations":[85],"(Bayer":[86],"2022).Hyperparameters":[89],"are":[90],"optimized":[91],"via":[92],"Optuna":[93],"(Akiba":[94],"2019)":[97],"maximize":[99],"macro-F1":[100,105],"performance.Our":[101],"method":[102],"achieves":[103],"score":[106],"of":[107],"0.65":[108],"on":[109],"official":[111],"test":[112],"set,":[113],"surpassing":[114],"strongest":[116],"single":[117],"0.04":[120],"outperforming":[122],"competitive":[123],"baselines":[125],"such":[126],"as":[127],"mBERT":[128],"LLaMA-based":[130],"large":[132],"language":[133],"models.These":[134],"results":[135],"demonstrate":[136],"linguistic":[140],"representations":[141],"targeted":[143],"substantially":[145],"improves":[146],"robustness":[147],"across":[148],"dialects":[149],"addresses":[151],"class":[152],"imbalance":[153],"classification.":[160]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-08T00:00:00"}