{"id":"https://openalex.org/W4415745001","doi":"https://doi.org/10.1109/hpcc67675.2025.00052","title":"A Keyword Exchange-Based Data Augmentation Method for Low-Resource Neural Machine Translation","display_name":"A Keyword Exchange-Based Data Augmentation Method for Low-Resource Neural Machine Translation","publication_year":2025,"publication_date":"2025-08-13","ids":{"openalex":"https://openalex.org/W4415745001","doi":"https://doi.org/10.1109/hpcc67675.2025.00052"},"language":null,"primary_location":{"id":"doi:10.1109/hpcc67675.2025.00052","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcc67675.2025.00052","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on High Performance Computing and Communications (HPCC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5038745722","display_name":"Hong Yan","orcid":"https://orcid.org/0000-0003-1834-8956"},"institutions":[{"id":"https://openalex.org/I4210095020","display_name":"Yingkou Institute of Technology","ror":"https://ror.org/00se3rd97","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210095020"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Yan","raw_affiliation_strings":["Yingkou Institute of Technology,Yingkou,Liaoning Province"],"raw_orcid":"https://orcid.org/0000-0003-1834-8956","affiliations":[{"raw_affiliation_string":"Yingkou Institute of Technology,Yingkou,Liaoning Province","institution_ids":["https://openalex.org/I4210095020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041771592","display_name":"Fuxue Li","orcid":"https://orcid.org/0000-0002-2878-6119"},"institutions":[{"id":"https://openalex.org/I4210095020","display_name":"Yingkou Institute of Technology","ror":"https://ror.org/00se3rd97","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210095020"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fuxue Li","raw_affiliation_strings":["Yingkou Institute of Technology,Yingkou,Liaoning Province"],"raw_orcid":"https://orcid.org/0000-0002-2878-6119","affiliations":[{"raw_affiliation_string":"Yingkou Institute of Technology,Yingkou,Liaoning Province","institution_ids":["https://openalex.org/I4210095020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039784805","display_name":"Peijun Xie","orcid":"https://orcid.org/0009-0008-0661-742X"},"institutions":[{"id":"https://openalex.org/I4210095020","display_name":"Yingkou Institute of Technology","ror":"https://ror.org/00se3rd97","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210095020"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Penjun Xie","raw_affiliation_strings":["Yingkou Institute of Technology,Yingkou,Liaoning Province"],"raw_orcid":"https://orcid.org/0009-0008-0661-742X","affiliations":[{"raw_affiliation_string":"Yingkou Institute of Technology,Yingkou,Liaoning Province","institution_ids":["https://openalex.org/I4210095020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082737480","display_name":"Chuncheng Chi","orcid":"https://orcid.org/0009-0008-2035-5892"},"institutions":[{"id":"https://openalex.org/I4210095020","display_name":"Yingkou Institute of Technology","ror":"https://ror.org/00se3rd97","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210095020"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuncheng Chi","raw_affiliation_strings":["Yingkou Institute of Technology,Yingkou,Liaoning Province"],"raw_orcid":"https://orcid.org/0009-0008-2035-5892","affiliations":[{"raw_affiliation_string":"Yingkou Institute of Technology,Yingkou,Liaoning Province","institution_ids":["https://openalex.org/I4210095020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018688986","display_name":"Qingfeng Cai","orcid":"https://orcid.org/0009-0008-0974-1215"},"institutions":[{"id":"https://openalex.org/I4210095020","display_name":"Yingkou Institute of Technology","ror":"https://ror.org/00se3rd97","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210095020"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingfeng Cai","raw_affiliation_strings":["Yingkou Institute of Technology,Yingkou,Liaoning Province"],"raw_orcid":"https://orcid.org/0009-0008-0974-1215","affiliations":[{"raw_affiliation_string":"Yingkou Institute of Technology,Yingkou,Liaoning Province","institution_ids":["https://openalex.org/I4210095020"]}]},{"author_position":"last","author":{"id":null,"display_name":"Yantao Wang","orcid":"https://orcid.org/0009-0006-6676-470X"},"institutions":[{"id":"https://openalex.org/I4210095020","display_name":"Yingkou Institute of Technology","ror":"https://ror.org/00se3rd97","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210095020"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yantao Wang","raw_affiliation_strings":["Yingkou Institute of Technology,Yingkou,Liaoning Province"],"raw_orcid":"https://orcid.org/0009-0006-6676-470X","affiliations":[{"raw_affiliation_string":"Yingkou Institute of Technology,Yingkou,Liaoning Province","institution_ids":["https://openalex.org/I4210095020"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210095020"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.28180981,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"253","last_page":"258"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.8224999904632568,"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":0.8224999904632568,"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":0.09929999709129333,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.016899999231100082,"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/machine-translation","display_name":"Machine translation","score":0.847000002861023},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.6223000288009644},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5236999988555908},{"id":"https://openalex.org/keywords/bleu","display_name":"BLEU","score":0.5228999853134155},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4683000147342682},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.41929998993873596}],"concepts":[{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.847000002861023},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8442000150680542},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6474999785423279},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.6223000288009644},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5467000007629395},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5236999988555908},{"id":"https://openalex.org/C622187","wikidata":"https://www.wikidata.org/wiki/Q3500773","display_name":"BLEU","level":3,"score":0.5228999853134155},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4683000147342682},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.41929998993873596},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.40459999442100525},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3596999943256378},{"id":"https://openalex.org/C2985367798","wikidata":"https://www.wikidata.org/wiki/Q1346592","display_name":"Parallel corpora","level":3,"score":0.2881999909877777},{"id":"https://openalex.org/C109747225","wikidata":"https://www.wikidata.org/wiki/Q815758","display_name":"Scarcity","level":2,"score":0.28380000591278076},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.28220000863075256},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.26570001244544983},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2606000006198883}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpcc67675.2025.00052","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcc67675.2025.00052","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on High Performance Computing and Communications (HPCC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7910296204","display_name":null,"funder_award_id":"2024LNYKJ07","funder_id":"https://openalex.org/F4320323086","funder_display_name":"Natural Science Foundation of Liaoning Province"}],"funders":[{"id":"https://openalex.org/F4320323086","display_name":"Natural Science Foundation of Liaoning Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2124807415","https://openalex.org/W2561274697","https://openalex.org/W2610850660","https://openalex.org/W2886095922","https://openalex.org/W2887516053","https://openalex.org/W2888519496","https://openalex.org/W2889326796","https://openalex.org/W2902614977","https://openalex.org/W2905266130","https://openalex.org/W2933138175","https://openalex.org/W2946068894","https://openalex.org/W2962696859","https://openalex.org/W2963088995","https://openalex.org/W2963216553","https://openalex.org/W2963545917","https://openalex.org/W2964199361"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,9,67],"Transformer-based":[3,182],"architectures":[4],"have":[5],"established":[6],"new":[7],"benchmarks":[8,158],"neural":[10],"machine":[11],"translation":[12,46,65,157],"(NMT),":[13],"though":[14],"their":[15,136],"efficacy":[16],"remains":[17],"constrained":[18],"by":[19],"the":[20,36,108,148,160],"availability":[21],"of":[22,38,175],"large-scale":[23],"parallel":[24],"corpora.":[25],"This":[26],"limitation":[27],"becomes":[28],"particularly":[29],"pronounced":[30],"for":[31],"low-resource":[32,156],"language":[33,98],"pairs,":[34],"where":[35],"scarcity":[37],"bilingual":[39],"training":[40,150],"data":[41,59,187],"often":[42],"leads":[43],"to":[44,63,86,115,179],"suboptimal":[45],"performance.":[47],"To":[48],"address":[49],"this":[50],"challenge,":[51],"we":[52],"introduce":[53],"Keyword":[54],"Exchange":[55],"(KE),":[56],"a":[57,75,141,170,180],"novel":[58],"augmentation":[60,188],"framework":[61],"designed":[62],"enhance":[64],"quality":[66],"data-scarce":[68],"scenarios.":[69],"The":[70,101],"proposed":[71],"methodology":[72],"operates":[73],"through":[74],"three-stage":[76],"pipeline:":[77],"(1)":[78],"A":[79],"selective":[80],"filtering":[81],"approach":[82,168],"is":[83,104],"first":[84],"applied":[85],"identify":[87],"and":[88,96],"retain":[89],"high-quality":[90],"sentence":[91],"pairs":[92],"from":[93],"both":[94],"source":[95],"target":[97],"corpora;":[99],"(2)":[100],"KE":[102],"algorithm":[103],"then":[105],"deployed":[106],"on":[107],"filtered":[109],"target-side":[110],"sentences,":[111],"strategically":[112],"substituting":[113],"keywords":[114],"generate":[116],"syntactically":[117],"valid":[118],"yet":[119],"semantically":[120],"divergent":[121],"pseudo-monolingual":[122],"data;":[123],"(3)":[124],"Finally,":[125],"an":[126],"Alignment":[127],"Mixture":[128],"strategy":[129],"synthesizes":[130],"these":[131],"augmented":[132],"monolingual":[133],"fragments":[134],"with":[135],"corresponding":[137],"source-side":[138],"counterparts,":[139],"producing":[140],"robust":[142],"pseudo-parallel":[143],"corpus":[144],"that":[145],"significantly":[146],"expands":[147],"effective":[149],"set.":[151],"Empirical":[152],"validation":[153],"across":[154],"multiple":[155],"demonstrates":[159],"framework's":[161],"superiority":[162],"over":[163],"conventional":[164],"baselines.":[165],"Notably,":[166],"our":[167],"achieves":[169],"maximum":[171],"BLEU":[172],"score":[173],"improvement":[174],"0.74":[176],"points":[177],"compared":[178],"strong":[181],"baseline,":[183],"outperforming":[184],"several":[185],"state-of-the-art":[186],"techniques.":[189]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-31T00:00:00"}