{"id":"https://openalex.org/W7166873437","doi":"https://doi.org/10.18653/v1/2026.semeval-1.160","title":"pfr821 at SemEval-2026 Task 9: Multilingual Polarization Detection via Hybrid XLM-RoBERTa with Targeted Data Augmentation and Imbalance-Aware Training","display_name":"pfr821 at SemEval-2026 Task 9: Multilingual Polarization Detection via Hybrid XLM-RoBERTa with Targeted Data Augmentation and Imbalance-Aware Training","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166873437","doi":"https://doi.org/10.18653/v1/2026.semeval-1.160"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.semeval-1.160","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.semeval-1.160","pdf_url":"https://aclanthology.org/2026.semeval-1.160.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 20th International Workshop on Semantic Evaluation (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.semeval-1.160.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139759402","display_name":"Antoine Durand","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Antoine Durand","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139807176","display_name":"R\u00e9mi Hamon","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"R\u00e9mi Hamon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139802082","display_name":"Matthieu Pereira","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Matthieu Pereira","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139843146","display_name":"Nathan Boucneau","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nathan Boucneau","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139817139","display_name":"Paul Cintra","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Paul Cintra","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.8619268,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1169","last_page":"1174"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.19699999690055847,"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":0.19699999690055847,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.11819999665021896,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.05550000071525574,"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/task","display_name":"Task (project management)","score":0.539900004863739},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4975000023841858},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.44679999351501465},{"id":"https://openalex.org/keywords/polarization","display_name":"Polarization (electrochemistry)","score":0.3447999954223633},{"id":"https://openalex.org/keywords/data-collection","display_name":"Data collection","score":0.2953999936580658}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6212999820709229},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.539900004863739},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4975000023841858},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45840001106262207},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.44679999351501465},{"id":"https://openalex.org/C205049153","wikidata":"https://www.wikidata.org/wiki/Q2698605","display_name":"Polarization (electrochemistry)","level":2,"score":0.3447999954223633},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.2953999936580658},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.28679999709129333},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.23649999499320984},{"id":"https://openalex.org/C163985040","wikidata":"https://www.wikidata.org/wiki/Q1172399","display_name":"Data acquisition","level":2,"score":0.22939999401569366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.semeval-1.160","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.semeval-1.160","pdf_url":"https://aclanthology.org/2026.semeval-1.160.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 20th International Workshop on Semantic Evaluation (2026)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.semeval-1.160","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.semeval-1.160","pdf_url":"https://aclanthology.org/2026.semeval-1.160.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 20th International Workshop on Semantic Evaluation (2026)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320319860","display_name":"Institut Polytechnique de Paris","ror":null},{"id":"https://openalex.org/F4320334537","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166873437.pdf","grobid_xml":"https://content.openalex.org/works/W7166873437.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"HYPOLDET,":[3],"the":[4,50,57,91,128],"system":[5],"submitted":[6],"by":[7],"team":[8],"pfr821":[9],"to":[10,52],"SemEval-2026":[11],"Task":[12],"9":[13],"(Polarization":[14],"Detection,":[15],"Subtask":[16],"1),":[17],"a":[18,36,42,65,99,121],"binary":[19],"classification":[20],"task":[21],"over":[22],"22":[23],"typologically":[24],"diverse":[25],"languages.Our":[26],"approach":[27],"combines":[28],"three":[29],"complementary":[30],"contributions.We":[31],"first":[32],"extend":[33],"XLM-RoBERTa-Large":[34],"with":[35],"custom":[37],"transformer":[38],"encoder":[39],"layer":[40],"and":[41,79,107,120,134],"learned":[43],"attentionbased":[44],"pooling":[45],"mechanism":[46],"(Hybrid":[47],"Architecture),":[48],"allowing":[49],"model":[51,112],"aggregate":[53],"tokenlevel":[54],"signals":[55],"beyond":[56],"[CLS]":[58],"representation.We":[59],"then":[60],"augment":[61],"training":[62,92],"data":[63,84],"through":[64,94],"targeted":[66],"LLM-based":[67],"synthetic":[68],"generation":[69],"pipeline":[70],"(Grok":[71],"API),":[72],"producing":[73],"culturally":[74],"grounded":[75],"examples":[76],"for":[77,131,137],"low-resource":[78],"imbalanced":[80],"languages.Finally,":[81],"independently":[82],"of":[83,118],"augmentation,":[85],"we":[86],"address":[87],"class":[88],"imbalance":[89],"at":[90],"level":[93],"an":[95,114],"imbalance-aware":[96],"regime":[97],"combining":[98],"per-language":[100],"balanced":[101],"batch":[102],"sampler,":[103],"weighted":[104],"focal":[105],"loss,":[106],"label":[108],"smoothing.Our":[109],"best":[110],"single":[111],"achieves":[113],"unweighted":[115],"macro-averaged":[116],"F1":[117],"0.796,":[119],"lightweight":[122],"ensemble":[123],"reaches":[124],"0.798,":[125],"ranking":[126],"in":[127],"top":[129],"10":[130],"7":[132],"languages":[133],"2nd":[135],"place":[136],"Hausa.":[138]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}