{"id":"https://openalex.org/W4416034124","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1177","title":"Data Augmentation for Maltese NLP using Transliterated and Machine Translated Arabic Data","display_name":"Data Augmentation for Maltese NLP using Transliterated and Machine Translated Arabic Data","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034124","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1177"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1177","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1177","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1177.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.1177.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051863994","display_name":"Kurt Micallef","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kurt Micallef","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084517393","display_name":"Nizar Habash","orcid":"https://orcid.org/0000-0002-1831-3457"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nizar Habash","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5086259576","display_name":"Claudia Borg","orcid":"https://orcid.org/0000-0001-8704-6893"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Claudia Borg","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":"21580","last_page":"21590"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.8251000046730042,"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":0.8251000046730042,"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/T10028","display_name":"Topic Modeling","score":0.03449999913573265,"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/T13912","display_name":"Language, Linguistics, Cultural Analysis","score":0.016499999910593033,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/maltese","display_name":"Maltese","score":0.5921000242233276},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.545799970626831},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.24500000476837158},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.24469999969005585},{"id":"https://openalex.org/keywords/transliteration","display_name":"Transliteration","score":0.24279999732971191}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6891999840736389},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6776999831199646},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.642300009727478},{"id":"https://openalex.org/C2775911240","wikidata":"https://www.wikidata.org/wiki/Q9166","display_name":"Maltese","level":2,"score":0.5921000242233276},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.545799970626831},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.39340001344680786},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.24500000476837158},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.24469999969005585},{"id":"https://openalex.org/C520968082","wikidata":"https://www.wikidata.org/wiki/Q134550","display_name":"Transliteration","level":2,"score":0.24279999732971191},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.21660000085830688}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.1177","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1177","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1177.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.1177","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1177","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1177.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/W4416034124.pdf","grobid_xml":"https://content.openalex.org/works/W4416034124.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Maltese":[0,53,93,114],"is":[1,26],"a":[2,33],"unique":[3],"Semitic":[4,22],"language":[5,55],"that":[6,90,108],"has":[7],"evolved":[8],"under":[9],"extensive":[10],"influence":[11],"from":[12],"Romance":[13],"and":[14,19,37,76,103,106],"Germanic":[15],"languages,":[16],"particularly":[17],"Italian":[18],"English.Despite":[20],"its":[21,24,38],"roots,":[23],"orthography":[25],"based":[27],"on":[28,101],"the":[29,96],"Latin":[30],"script,":[31],"creating":[32],"gap":[34],"between":[35],"it":[36],"closest":[39],"linguistic":[40],"relatives":[41],"in":[42],"Arabic.In":[43],"this":[44],"paper,":[45],"we":[46,84],"explore":[47],"whether":[48],"Arabic-language":[49],"resources":[50],"can":[51,111],"support":[52],"natural":[54],"processing":[56],"(NLP)":[57],"through":[58],"cross-lingual":[59],"augmentation":[60,110],"techniques.We":[61],"investigate":[62],"multiple":[63],"strategies":[64],"for":[65],"aligning":[66],"Arabic":[67],"textual":[68],"data":[69],"with":[70],"Maltese,":[71],"including":[72],"various":[73],"transliteration":[74,88],"schemes":[75],"machine":[77],"translation":[78],"(MT)":[79],"approaches.As":[80],"part":[81],"of":[82,98],"this,":[83],"also":[85],"introduce":[86],"novel":[87],"systems":[89],"better":[91],"represent":[92],"orthography.We":[94],"evaluate":[95],"impact":[97],"these":[99],"augmentations":[100],"monolingual":[102],"mutlilingual":[104],"models":[105],"demonstrate":[107],"Arabic-based":[109],"significantly":[112],"benefit":[113],"NLP":[115],"tasks.":[116]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-08T00:00:00"}
