{"id":"https://openalex.org/W4416037784","doi":"https://doi.org/10.18653/v1/2025.arabicnlp-sharedtasks.111","title":"CultranAI at PalmX 2025: Data Augmentation for Cultural Knowledge Representation","display_name":"CultranAI at PalmX 2025: Data Augmentation for Cultural Knowledge Representation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416037784","doi":"https://doi.org/10.18653/v1/2025.arabicnlp-sharedtasks.111"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.arabicnlp-sharedtasks.111","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.arabicnlp-sharedtasks.111","pdf_url":"https://aclanthology.org/2025.arabicnlp-sharedtasks.111.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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.arabicnlp-sharedtasks.111.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120049266","display_name":"Hunzalah Hassan Bhatti","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hunzalah Hassan Bhatti","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104100255","display_name":"Youssef Ahmed","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Youssef Ahmed","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021570815","display_name":"Md. Arid Hasan","orcid":"https://orcid.org/0000-0001-7916-614X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Md Arid Hasan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5053436179","display_name":"Firoj Alam","orcid":"https://orcid.org/0000-0001-7172-1997"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Firoj Alam","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":0.22869198,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"809","last_page":"817"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12090","display_name":"Language and cultural evolution","score":0.12389999628067017,"subfield":{"id":"https://openalex.org/subfields/3316","display_name":"Cultural Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12090","display_name":"Language and cultural evolution","score":0.12389999628067017,"subfield":{"id":"https://openalex.org/subfields/3316","display_name":"Cultural Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.09489999711513519,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.05730000138282776,"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/representation","display_name":"Representation (politics)","score":0.4219000041484833},{"id":"https://openalex.org/keywords/knowledge-representation-and-reasoning","display_name":"Knowledge representation and reasoning","score":0.41929998993873596},{"id":"https://openalex.org/keywords/knowledge-based-systems","display_name":"Knowledge-based systems","score":0.31119999289512634},{"id":"https://openalex.org/keywords/cultural-knowledge","display_name":"Cultural knowledge","score":0.29750001430511475},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.28049999475479126},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.27059999108314514}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.567799985408783},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4496999979019165},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4219000041484833},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.41929998993873596},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3873000144958496},{"id":"https://openalex.org/C115925183","wikidata":"https://www.wikidata.org/wiki/Q1412694","display_name":"Knowledge-based systems","level":2,"score":0.31119999289512634},{"id":"https://openalex.org/C2994055011","wikidata":"https://www.wikidata.org/wiki/Q210272","display_name":"Cultural knowledge","level":2,"score":0.29750001430511475},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.28049999475479126},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2687999904155731},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.26510000228881836},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2603999972343445},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2574000060558319},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.2567000091075897},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.25189998745918274}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.arabicnlp-sharedtasks.111","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.arabicnlp-sharedtasks.111","pdf_url":"https://aclanthology.org/2025.arabicnlp-sharedtasks.111.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.111","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.arabicnlp-sharedtasks.111","pdf_url":"https://aclanthology.org/2025.arabicnlp-sharedtasks.111.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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416037784.pdf","grobid_xml":"https://content.openalex.org/works/W4416037784.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1,82],"paper,":[2],"we":[3,50],"report":[4],"our":[5,96],"participation":[6],"to":[7,36,45],"the":[8,38,42,47,55,74,78,85,92,108,124],"PalmX":[9,48,109],"cultural":[10,30],"evaluation":[11],"shared":[12],"task.Our":[13],"system,":[14],"CultranAI,":[15],"focused":[16],"on":[17,84,107],"data":[18],"augmentation":[19],"and":[20,58],"LoRA":[21],"fine-tuning":[22],"of":[23,63,89,104,116],"large":[24],"language":[25],"models":[26],"(LLMs)":[27],"for":[28,41,123],"Arabic":[29],"knowledge":[31],"representation.We":[32],"benchmarked":[33],"several":[34],"LLMs":[35],"identify":[37],"best-performing":[39],"model":[40,76,83],"task.In":[43],"addition":[44],"utilizing":[46],"dataset,":[49],"augmented":[51,87],"it":[52,112],"by":[53],"incorporating":[54],"Palm":[56],"dataset":[57,62,88],"curated":[59],"a":[60],"new":[61],"over":[64],"22K":[65],"culturally":[66],"grounded":[67],"multiple-choice":[68],"questions":[69],"(MCQs).Our":[70],"experiments":[71],"showed":[72],"that":[73],"Fanar-1-9B-Instruct":[75],"achieved":[77,113],"highest":[79],"performance.We":[80],"fine-tuned":[81],"combined":[86],"22K+":[90],"MCQs.On":[91],"blind":[93],"test":[94],"set,":[95,111],"submitted":[97],"system":[98],"ranked":[99],"5th":[100],"with":[101],"an":[102,114],"accuracy":[103,115],"70.50%,":[105],"while":[106],"development":[110],"84.1%.We":[117],"made":[118],"experimental":[119],"scripts":[120],"publicly":[121],"available":[122],"community.":[125]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-08T00:00:00"}
