{"id":"https://openalex.org/W4411358818","doi":"https://doi.org/10.1109/access.2025.3580635","title":"RMixDA: A Random Compound Data Augmentation Operation Framework for Neural Machine Translation","display_name":"RMixDA: A Random Compound Data Augmentation Operation Framework for Neural Machine Translation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4411358818","doi":"https://doi.org/10.1109/access.2025.3580635"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3580635","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3580635","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3580635","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Huijun Wang","orcid":"https://orcid.org/0009-0007-8423-4013"},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huijun Wang","raw_affiliation_strings":["School of Computer, Electronics Information, Guangxi University, Nanning, China"],"raw_orcid":"https://orcid.org/0009-0007-8423-4013","affiliations":[{"raw_affiliation_string":"School of Computer, Electronics Information, Guangxi University, Nanning, China","institution_ids":["https://openalex.org/I150807315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065572611","display_name":"Xiaojing Du","orcid":"https://orcid.org/0000-0002-5199-7192"},"institutions":[{"id":"https://openalex.org/I170239107","display_name":"University of South Australia","ror":"https://ror.org/01p93h210","country_code":"AU","type":"education","lineage":["https://openalex.org/I170239107"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xiaojing Du","raw_affiliation_strings":["STEM, University of South Australia, Adelaide, SA, Australia","STEM, University of South Australia, Adelaide, Australia"],"raw_orcid":"https://orcid.org/0000-0002-5199-7192","affiliations":[{"raw_affiliation_string":"STEM, University of South Australia, Adelaide, SA, Australia","institution_ids":["https://openalex.org/I170239107"]},{"raw_affiliation_string":"STEM, University of South Australia, Adelaide, Australia","institution_ids":["https://openalex.org/I170239107"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040423423","display_name":"Xinkun Hao","orcid":null},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinkun Hao","raw_affiliation_strings":["School of Computer, Electronics Information, Guangxi University, Nanning, China"],"raw_orcid":"https://orcid.org/0009-0005-4235-1014","affiliations":[{"raw_affiliation_string":"School of Computer, Electronics Information, Guangxi University, Nanning, China","institution_ids":["https://openalex.org/I150807315"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06456025,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"13","issue":null,"first_page":"105101","last_page":"105112"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9897000193595886,"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":0.9897000193595886,"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/computer-science","display_name":"Computer science","score":0.7637016773223877},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5165256857872009},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.414957195520401},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3504079282283783}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7637016773223877},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5165256857872009},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.414957195520401},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3504079282283783}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2025.3580635","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3580635","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:37166bcc963c4a709458145bf19fcdf6","is_oa":true,"landing_page_url":"https://doaj.org/article/37166bcc963c4a709458145bf19fcdf6","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":"IEEE Access, Vol 13, Pp 105101-105112 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3580635","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3580635","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W1980318031","https://openalex.org/W1987125632","https://openalex.org/W2003582562","https://openalex.org/W2101105183","https://openalex.org/W2111798208","https://openalex.org/W2610850660","https://openalex.org/W2740565324","https://openalex.org/W2741049976","https://openalex.org/W2765407302","https://openalex.org/W2888519496","https://openalex.org/W2889326796","https://openalex.org/W2922293812","https://openalex.org/W2950651087","https://openalex.org/W2963823140","https://openalex.org/W2964048171","https://openalex.org/W2970674617","https://openalex.org/W2971296908","https://openalex.org/W2984051011","https://openalex.org/W2992308087","https://openalex.org/W2998184481","https://openalex.org/W3035542229","https://openalex.org/W3035577668","https://openalex.org/W3100268441","https://openalex.org/W3154559866","https://openalex.org/W3174828871","https://openalex.org/W3201295503","https://openalex.org/W3201915713","https://openalex.org/W4225368778","https://openalex.org/W4287829148","https://openalex.org/W4309028162","https://openalex.org/W4312638656","https://openalex.org/W4377291249","https://openalex.org/W4385245566","https://openalex.org/W4385392828","https://openalex.org/W4389520190","https://openalex.org/W4399091736","https://openalex.org/W4404823372","https://openalex.org/W4409282456","https://openalex.org/W4409569111","https://openalex.org/W6605452230","https://openalex.org/W6640036494","https://openalex.org/W6674650171","https://openalex.org/W6722524744","https://openalex.org/W6727690538","https://openalex.org/W6734807902","https://openalex.org/W6739826697","https://openalex.org/W6745388339","https://openalex.org/W6745740328","https://openalex.org/W6746141323","https://openalex.org/W6746208923","https://openalex.org/W6783973398","https://openalex.org/W6788811087","https://openalex.org/W6790312409","https://openalex.org/W6797110910"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W3011059803","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890"],"abstract_inverted_index":{"In":[0],"Neural":[1],"Machine":[2],"Translation":[3],"(NMT),":[4],"data":[5,19,28,93,112,165,183,203,222],"augmentation":[6,94,113,223],"is":[7,29,185,188],"an":[8,98],"effective":[9],"method":[10,180],"for":[11,152,181,219],"improving":[12],"model":[13,206],"robustness":[14,69],"by":[15,190],"generating":[16],"diverse":[17,149,221],"augmented":[18,27,150,164,182,202],"from":[20],"existing":[21],"datasets.":[22],"Typically,":[23],"the":[24,56,68,105,191,198,212],"quality":[25,184,204],"of":[26,48,58,72,101,214],"evaluated":[30],"based":[31],"on":[32,44],"its":[33,217],"similarity":[34,155,173],"and":[35,70,128,156,205,216],"diversity":[36],"to":[37,53,147,171,196],"training":[38],"data.":[39,63],"Current":[40],"approaches":[41],"often":[42],"rely":[43],"a":[45,80,143,177],"single":[46],"type":[47],"operation,":[49],"limiting":[50],"their":[51],"ability":[52],"fully":[54],"capture":[55],"range":[57],"possible":[59],"variations":[60],"in":[61],"real-world":[62],"This":[64],"limitation":[65],"will":[66],"affect":[67],"generalization":[71],"model.":[73],"To":[74],"address":[75],"this,":[76],"we":[77],"propose":[78],"RMixDA:":[79],"Random":[81],"Mixed":[82],"Algorithm":[83],"Framework":[84],"For":[85],"Data":[86],"Augmentation,":[87],"which":[88,110,187],"dynamically":[89],"integrates":[90],"multiple":[91],"NMT-oriented":[92],"methods.":[95],"RMixDA":[96,215],"defines":[97],"extensible":[99],"collection":[100],"multi-augmentation":[102],"operations":[103,139],"using":[104,142],"Backus-Naur":[106],"Form":[107],"(BNF)":[108],"framework,":[109],"categorizes":[111],"methods":[114],"into":[115],"pre-embedding":[116],"(<italic":[117,123,130],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[118,120,124,126,131,133,135],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">pre</i>_<italic":[119],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">embed</i>_op),":[121],"embedding":[122],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">embed</i>_<italic":[125,134],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">op</i>)":[127,136],"post-embedding":[129],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">post</i>_<italic":[132],"levels.":[137],"These":[138],"are":[140],"combined":[141],"random":[144],"walk":[145],"algorithm":[146],"generate":[148],"data,":[151],"maintaining":[153],"both":[154],"diversity.":[157],"We":[158],"further":[159],"incorporate":[160],"contrastive":[161],"learning,":[162],"identifying":[163],"as":[166],"positive":[167,199],"or":[168],"negative":[169],"samples":[170],"evaluate":[172],"more":[174],"effectively.":[175],"Additionally,":[176],"novel":[178],"evaluation":[179],"introduced,":[186],"regularized":[189],"NMT":[192],"model\u2019s":[193],"loss":[194],"function":[195],"improve":[197],"correlation":[200],"between":[201],"training.":[207],"Extensive":[208],"experimental":[209],"studies":[210],"demonstrate":[211],"effectiveness":[213],"scalability":[218],"integrating":[220],"operations.":[224]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}