{"id":"https://openalex.org/W3203011138","doi":"https://doi.org/10.3390/s21196509","title":"A Transformer-Based Neural Machine Translation Model for Arabic Dialects That Utilizes Subword Units","display_name":"A Transformer-Based Neural Machine Translation Model for Arabic Dialects That Utilizes Subword Units","publication_year":2021,"publication_date":"2021-09-29","ids":{"openalex":"https://openalex.org/W3203011138","doi":"https://doi.org/10.3390/s21196509","mag":"3203011138","pmid":"https://pubmed.ncbi.nlm.nih.gov/34640835"},"language":"en","primary_location":{"id":"doi:10.3390/s21196509","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s21196509","pdf_url":"https://www.mdpi.com/1424-8220/21/19/6509/pdf?version=1632993050","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1424-8220/21/19/6509/pdf?version=1632993050","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022577339","display_name":"Laith H. Baniata","orcid":"https://orcid.org/0000-0002-0029-0859"},"institutions":[{"id":"https://openalex.org/I31419693","display_name":"Kyungpook National University","ror":"https://ror.org/040c17130","country_code":"KR","type":"education","lineage":["https://openalex.org/I31419693"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Laith H. Baniata","raw_affiliation_strings":["School of Computer Science and Engineering, Kyungpook National University, 80 Daehak-ro, Buk-gu, Daegu 41566, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Kyungpook National University, 80 Daehak-ro, Buk-gu, Daegu 41566, Korea","institution_ids":["https://openalex.org/I31419693"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059111449","display_name":"Isaac K. E. Ampomah","orcid":"https://orcid.org/0000-0003-2466-1981"},"institutions":[{"id":"https://openalex.org/I190082696","display_name":"Durham University","ror":"https://ror.org/01v29qb04","country_code":"GB","type":"education","lineage":["https://openalex.org/I190082696"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Isaac. K. E. Ampomah","raw_affiliation_strings":["Department of Computer Science, Durham University, Stockton Road, Durham DH1 3LE, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Durham University, Stockton Road, Durham DH1 3LE, UK","institution_ids":["https://openalex.org/I190082696"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101599446","display_name":"Seyoung Park","orcid":"https://orcid.org/0000-0002-9447-3022"},"institutions":[{"id":"https://openalex.org/I31419693","display_name":"Kyungpook National University","ror":"https://ror.org/040c17130","country_code":"KR","type":"education","lineage":["https://openalex.org/I31419693"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Seyoung Park","raw_affiliation_strings":["School of Computer Science and Engineering, Kyungpook National University, 80 Daehak-ro, Buk-gu, Daegu 41566, Korea"],"raw_orcid":"https://orcid.org/0000-0002-9447-3022","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Kyungpook National University, 80 Daehak-ro, Buk-gu, Daegu 41566, Korea","institution_ids":["https://openalex.org/I31419693"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101599446"],"corresponding_institution_ids":["https://openalex.org/I31419693"],"apc_list":{"value":2400,"currency":"CHF","value_usd":2598},"apc_paid":{"value":2400,"currency":"CHF","value_usd":2598},"fwci":3.218,"has_fulltext":true,"cited_by_count":31,"citation_normalized_percentile":{"value":0.93209069,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"21","issue":"19","first_page":"6509","last_page":"6509"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.998199999332428,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9677000045776367,"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/computer-science","display_name":"Computer science","score":0.7580543756484985},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.7475067377090454},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7021167278289795},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6712232828140259},{"id":"https://openalex.org/keywords/modern-standard-arabic","display_name":"Modern Standard Arabic","score":0.6039051413536072},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6000258326530457},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.5722928047180176},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.49491065740585327},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.4816912114620209},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48009565472602844},{"id":"https://openalex.org/keywords/vernacular","display_name":"Vernacular","score":0.4636681377887726},{"id":"https://openalex.org/keywords/equivalence","display_name":"Equivalence (formal languages)","score":0.4523424208164215},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4220081567764282},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.337383896112442},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10997244715690613}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7580543756484985},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7475067377090454},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7021167278289795},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6712232828140259},{"id":"https://openalex.org/C2778243841","wikidata":"https://www.wikidata.org/wiki/Q56467","display_name":"Modern Standard Arabic","level":3,"score":0.6039051413536072},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6000258326530457},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.5722928047180176},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.49491065740585327},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.4816912114620209},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48009565472602844},{"id":"https://openalex.org/C2780386941","wikidata":"https://www.wikidata.org/wiki/Q1036511","display_name":"Vernacular","level":2,"score":0.4636681377887726},{"id":"https://openalex.org/C2780069185","wikidata":"https://www.wikidata.org/wiki/Q7977945","display_name":"Equivalence (formal languages)","level":2,"score":0.4523424208164215},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4220081567764282},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.337383896112442},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10997244715690613},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D014825","descriptor_name":"Vocabulary","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D014825","descriptor_name":"Vocabulary","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D014825","descriptor_name":"Vocabulary","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":5,"locations":[{"id":"doi:10.3390/s21196509","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s21196509","pdf_url":"https://www.mdpi.com/1424-8220/21/19/6509/pdf?version=1632993050","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},{"id":"pmid:34640835","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34640835","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors (Basel, Switzerland)","raw_type":null},{"id":"pmh:oai:doaj.org/article:2db59e03f40d453ab3adda823baa4b24","is_oa":true,"landing_page_url":"https://doaj.org/article/2db59e03f40d453ab3adda823baa4b24","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors, Vol 21, Iss 19, p 6509 (2021)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/1424-8220/21/19/6509/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/s21196509","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors; Volume 21; Issue 19; Pages: 6509","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:8512729","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8512729","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors (Basel)","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/s21196509","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s21196509","pdf_url":"https://www.mdpi.com/1424-8220/21/19/6509/pdf?version=1632993050","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7799999713897705,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2791559250","display_name":null,"funder_award_id":"4199990214394","funder_id":"https://openalex.org/F4320321272","funder_display_name":"Kyungpook National University"}],"funders":[{"id":"https://openalex.org/F4320321272","display_name":"Kyungpook National University","ror":"https://ror.org/040c17130"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3203011138.pdf","grobid_xml":"https://content.openalex.org/works/W3203011138.grobid-xml"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W181901128","https://openalex.org/W1753482797","https://openalex.org/W1902237438","https://openalex.org/W2064675550","https://openalex.org/W2100664567","https://openalex.org/W2101105183","https://openalex.org/W2103078213","https://openalex.org/W2118434577","https://openalex.org/W2121879602","https://openalex.org/W2133564696","https://openalex.org/W2139604620","https://openalex.org/W2157331557","https://openalex.org/W2194775991","https://openalex.org/W2251948394","https://openalex.org/W2394969460","https://openalex.org/W2594047108","https://openalex.org/W2741157881","https://openalex.org/W2751193242","https://openalex.org/W2754166059","https://openalex.org/W2757281913","https://openalex.org/W2758137671","https://openalex.org/W2764285152","https://openalex.org/W2768123736","https://openalex.org/W2786520898","https://openalex.org/W2798638375","https://openalex.org/W2800965800","https://openalex.org/W2810144967","https://openalex.org/W2884083742","https://openalex.org/W2899182573","https://openalex.org/W2902441267","https://openalex.org/W2905123482","https://openalex.org/W2912351236","https://openalex.org/W2918555272","https://openalex.org/W2956281465","https://openalex.org/W2962784628","https://openalex.org/W2962944953","https://openalex.org/W2969856879","https://openalex.org/W2972498556","https://openalex.org/W2972978035","https://openalex.org/W3037496935","https://openalex.org/W6631190155","https://openalex.org/W6679436768","https://openalex.org/W6685229248","https://openalex.org/W6690971519","https://openalex.org/W6737778391","https://openalex.org/W6739901393","https://openalex.org/W6752073440","https://openalex.org/W6758657797","https://openalex.org/W6759455113","https://openalex.org/W6780226713"],"related_works":["https://openalex.org/W2620283452","https://openalex.org/W4322750817","https://openalex.org/W2794347674","https://openalex.org/W4245232085","https://openalex.org/W2801712537","https://openalex.org/W587642979","https://openalex.org/W2894059694","https://openalex.org/W3173761424","https://openalex.org/W4299493485","https://openalex.org/W617130659"],"abstract_inverted_index":{"Languages":[0],"that":[1,45,51,83,96,180],"allow":[2],"free":[3],"word":[4,188],"order,":[5],"such":[6],"as":[7,60],"Arabic":[8,81,111,119,145,153,159,163,171,197,202],"dialects,":[9],"are":[10,57,148],"of":[11,20,27,62,103,126,141,194],"significant":[12],"difficulty":[13],"for":[14,42,80,131,144],"neural":[15,76],"machine":[16,77],"translation":[17,78,175,195],"(NMT)":[18],"because":[19],"many":[21],"scarce":[22],"words":[23,41,56,140],"and":[24,106,116,161,190],"the":[25,39,43,66,73,93,110,124,127,132,136,181,186,192],"inefficiency":[26],"NMT":[28,46],"systems":[29,47],"to":[30,156,166,173,199],"translate":[31],"these":[32],"words.":[33],"Unknown":[34],"Word":[35],"(UNK)":[36],"tokens":[37],"represent":[38],"out-of-vocabulary":[40],"reason":[44],"run":[48],"with":[49],"vocabulary":[50,108],"has":[52,97],"fixed":[53],"size.":[54],"Scarce":[55],"encoded":[58],"completely":[59],"sequences":[61],"subword":[63,85,104],"pieces":[64],"employing":[65],"Word-Piece":[67],"Model.":[68],"This":[69],"research":[70],"paper":[71],"introduces":[72],"first":[74],"Transformer-based":[75],"model":[79,95,183],"vernaculars":[82,198],"employs":[84],"units.":[86],"The":[87,101],"proposed":[88],"solution":[89],"is":[90],"based":[91],"on":[92],"Transformer":[94],"been":[98],"presented":[99],"lately.":[100],"use":[102],"units":[105],"shared":[107],"within":[109],"dialect":[112],"(the":[113,120],"source":[114],"language)":[115,122],"modern":[117,157],"standard":[118,158,201],"target":[121],"enhances":[123],"behavior":[125],"multi-head":[128],"attention":[129],"sublayers":[130],"encoder":[133],"by":[134],"obtaining":[135],"overall":[137],"dependencies":[138],"between":[139],"input":[142],"sentence":[143],"vernacular.":[146],"Experiments":[147],"carried":[149],"out":[150],"from":[151,196],"Levantine":[152],"vernacular":[154,164],"(LEV)":[155],"(MSA)":[160],"Maghrebi":[162],"(MAG)":[165],"MSA,":[167],"Gulf-MSA,":[168],"Nile-MSA,":[169],"Iraqi":[170],"(IRQ)":[172],"MSA":[174],"tasks.":[176],"Extensive":[177],"experiments":[178],"confirm":[179],"suggested":[182],"adequately":[184],"addresses":[185],"unknown":[187],"issue":[189],"boosts":[191],"quality":[193],"Modern":[200],"(MSA).":[203]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":4}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
