{"id":"https://openalex.org/W4416183244","doi":"https://doi.org/10.1109/idap68205.2025.11222271","title":"Enhancing Cebuano-English Neural Machine Translation Using Pseudo-Labeling and Transformer Architectures","display_name":"Enhancing Cebuano-English Neural Machine Translation Using Pseudo-Labeling and Transformer Architectures","publication_year":2025,"publication_date":"2025-09-06","ids":{"openalex":"https://openalex.org/W4416183244","doi":"https://doi.org/10.1109/idap68205.2025.11222271"},"language":"en","primary_location":{"id":"doi:10.1109/idap68205.2025.11222271","doi":"https://doi.org/10.1109/idap68205.2025.11222271","is_oa":false,"landing_page_url":"https://doi.org/10.1109/idap68205.2025.11222271","pdf_url":null,"source":{"id":"https://openalex.org/S4306498172","display_name":"International Artificial Intelligence and Data Processing Symposium (IDAP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 9th International Artificial Intelligence and Data Processing Symposium (IDAP)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120349545","display_name":"Paolo L. Pacaldo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I210563421","display_name":"Caraga State University","ror":"https://ror.org/00erb5q72","country_code":"PH","type":"education","lineage":["https://openalex.org/I210563421"]}],"countries":["PH"],"is_corresponding":false,"raw_author_name":"Paolo L. Pacaldo","raw_affiliation_strings":["Caraga State University,Department of Information Technology,Butuan City,Philippines"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Caraga State University,Department of Information Technology,Butuan City,Philippines","institution_ids":["https://openalex.org/I210563421"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075735598","display_name":"Junrie B. Matias","orcid":"https://orcid.org/0000-0001-9638-4667","observed_orcids":["https://orcid.org/0000-0001-9638-4667"]},"institutions":[{"id":"https://openalex.org/I210563421","display_name":"Caraga State University","ror":"https://ror.org/00erb5q72","country_code":"PH","type":"education","lineage":["https://openalex.org/I210563421"]}],"countries":["PH"],"is_corresponding":false,"raw_author_name":"Junrie B. Matias","raw_affiliation_strings":["School of Graduate Studies, Caraga State University,Butuan City,Philippines"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Graduate Studies, Caraga State University,Butuan City,Philippines","institution_ids":["https://openalex.org/I210563421"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067578352","display_name":"Jaymer M. Jayoma","orcid":"https://orcid.org/0000-0001-7063-2693","observed_orcids":["https://orcid.org/0000-0001-7063-2693"]},"institutions":[{"id":"https://openalex.org/I210563421","display_name":"Caraga State University","ror":"https://ror.org/00erb5q72","country_code":"PH","type":"education","lineage":["https://openalex.org/I210563421"]}],"countries":["PH"],"is_corresponding":false,"raw_author_name":"Jaymer M. Jayoma","raw_affiliation_strings":["Caraga State University,Department of Computer Science,Butuan City,Philippines"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Caraga State University,Department of Computer Science,Butuan City,Philippines","institution_ids":["https://openalex.org/I210563421"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079210661","display_name":"Gleen A. Dalaorao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I210563421","display_name":"Caraga State University","ror":"https://ror.org/00erb5q72","country_code":"PH","type":"education","lineage":["https://openalex.org/I210563421"]}],"countries":["PH"],"is_corresponding":false,"raw_author_name":"Gleen A. Dalaorao","raw_affiliation_strings":["Caraga State University,Department of Information Technology,Butuan City,Philippines"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Caraga State University,Department of Information Technology,Butuan City,Philippines","institution_ids":["https://openalex.org/I210563421"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Clark Justine Gonzales","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I210563421","display_name":"Caraga State University","ror":"https://ror.org/00erb5q72","country_code":"PH","type":"education","lineage":["https://openalex.org/I210563421"]}],"countries":["PH"],"is_corresponding":false,"raw_author_name":"Clark Justine Gonzales","raw_affiliation_strings":["Caraga State University,Department of Computer Science,Butuan City,Philippines"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Caraga State University,Department of Computer Science,Butuan City,Philippines","institution_ids":["https://openalex.org/I210563421"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5120398403","display_name":"John Michael F. Cutamora","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I210563421","display_name":"Caraga State University","ror":"https://ror.org/00erb5q72","country_code":"PH","type":"education","lineage":["https://openalex.org/I210563421"]}],"countries":["PH"],"is_corresponding":false,"raw_author_name":"John Michael Cutamora","raw_affiliation_strings":["Caraga State University,Department of Computer Science,Butuan City,Philippines"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Caraga State University,Department of Computer Science,Butuan City,Philippines","institution_ids":["https://openalex.org/I210563421"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I210563421"],"apc_list":null,"apc_paid":null,"fwci":0.368,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.66935543,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9945999979972839,"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":0.9945999979972839,"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":0.002899999963119626,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.0010000000474974513,"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/pseudo-labeling","display_name":"pseudo-labeling","score":0.8489999771118164},{"id":"https://openalex.org/keywords/transformer","display_name":"transformer models","score":0.4580000042915344},{"id":"https://openalex.org/keywords/marianmt","display_name":"MarianMT","score":0.9679999947547913},{"id":"https://openalex.org/keywords/low-resource-languages","display_name":"low-resource languages","score":0.8970000147819519},{"id":"https://openalex.org/keywords/confidence-filtering","display_name":"confidence filtering","score":0.652999997138977},{"id":"https://openalex.org/keywords/curriculum-learning","display_name":"curriculum learning","score":0.8190000057220459},{"id":"https://openalex.org/keywords/attention-maps","display_name":"attention maps","score":0.8140000104904175},{"id":"https://openalex.org/keywords/philippine-languages","display_name":"Philippine languages","score":0.8550000190734863}],"concepts":[{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.8745999932289124},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7943999767303467},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.704200029373169},{"id":"https://openalex.org/C622187","wikidata":"https://www.wikidata.org/wiki/Q3500773","display_name":"BLEU","level":3,"score":0.6789000034332275},{"id":"https://openalex.org/C2777413886","wikidata":"https://www.wikidata.org/wiki/Q3276013","display_name":"Fluency","level":2,"score":0.6488000154495239},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.6388000249862671},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5626000165939331},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5440999865531921},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5371000170707703},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5338000059127808},{"id":"https://openalex.org/C2986258472","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation system","level":3,"score":0.4756999909877777},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.451200008392334},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37929999828338623},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.34119999408721924},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.298799991607666},{"id":"https://openalex.org/C2986862884","wikidata":"https://www.wikidata.org/wiki/Q7553","display_name":"Language translation","level":3,"score":0.2939000129699707},{"id":"https://openalex.org/C135784402","wikidata":"https://www.wikidata.org/wiki/Q6958279","display_name":"Evaluation of machine translation","level":5,"score":0.265500009059906},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/idap68205.2025.11222271","doi":"https://doi.org/10.1109/idap68205.2025.11222271","is_oa":false,"landing_page_url":"https://doi.org/10.1109/idap68205.2025.11222271","pdf_url":null,"source":{"id":"https://openalex.org/S4306498172","display_name":"International Artificial Intelligence and Data Processing Symposium (IDAP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 9th International Artificial Intelligence and Data Processing Symposium (IDAP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2923622379","https://openalex.org/W2962784628","https://openalex.org/W3049491733","https://openalex.org/W3173162544","https://openalex.org/W3174697615","https://openalex.org/W3186748023","https://openalex.org/W3193077216","https://openalex.org/W3203734430","https://openalex.org/W4281770669","https://openalex.org/W4390678101","https://openalex.org/W4394573278"],"related_works":["https://openalex.org/W2911387498","https://openalex.org/W2969678104","https://openalex.org/W3180103694","https://openalex.org/W3120881350","https://openalex.org/W4387928929","https://openalex.org/W4200203993","https://openalex.org/W7167839474","https://openalex.org/W2998540408","https://openalex.org/W4286265005","https://openalex.org/W7131100807"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,19,38,52,72,96,131],"semi-supervised":[4],"neural":[5],"machine":[6],"translation":[7,14,90],"(NMT)":[8],"pipeline":[9],"that":[10,94,128],"significantly":[11],"improves":[12],"Cebuano$\\leftrightarrow$English":[13],"quality.":[15,91],"Our":[16],"approach":[17],"achieved":[18],"24.3-point":[20],"improvement":[21],"in":[22,89],"BLEU":[23],"score,":[24],"increasing":[25],"from":[26],"60.89":[27],"to":[28,70],"85.19,":[29],"while":[30,85],"maintaining":[31],"fluency":[32],"and":[33,62,82,103,112,133],"semantic":[34,83],"adequacy.":[35],"Starting":[36],"with":[37,67,99],"0.46-million-sentence":[39],"parallel":[40],"corpus,":[41],"we":[42],"forward-translated":[43],"2.4":[44],"million":[45],"monolingual":[46],"English":[47],"sentences":[48],"into":[49],"Cebuano":[50],"using":[51,59],"pseudo-labeling":[53,129],"method.":[54],"These":[55,125],"outputs":[56],"were":[57],"filtered":[58],"confidence":[60],"scores":[61],"length":[63],"ratios,":[64],"then":[65],"combined":[66],"gold-standard":[68,106],"data":[69,107],"retrain":[71],"Transformer-based":[73],"MarianMT":[74],"model.":[75],"The":[76],"final":[77],"system":[78],"preserved":[79],"structural":[80],"fidelity":[81],"accuracy":[84],"delivering":[86],"substantial":[87],"gains":[88],"Experiments":[92],"revealed":[93],"(i)":[95],"curriculum":[97],"beginning":[98],"70":[100],"%":[101,105],"pseudo-labeled":[102],"30":[104],"yields":[108],"the":[109,120],"fastest":[110],"convergence,":[111],"(ii)":[113],"attention":[114],"maps":[115],"remain":[116],"linguistically":[117],"coherent":[118],"despite":[119],"inclusion":[121],"of":[122],"synthetic":[123],"data.":[124],"findings":[126],"demonstrate":[127],"is":[130],"cost-effective":[132],"scalable":[134],"strategy":[135],"for":[136],"low-resource":[137],"Philippine":[138],"languages.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2025-11-11T00:00:00"}
