{"id":"https://openalex.org/W7205002971","doi":"https://doi.org/10.3390/computers15090576","title":"SSPA: Enhancing Pseudo-Corpus Quality on Tibetan Machine Translation via Semantic-Syntax Prealignment","display_name":"SSPA: Enhancing Pseudo-Corpus Quality on Tibetan Machine Translation via Semantic-Syntax Prealignment","publication_year":2026,"publication_date":"2026-09-02","ids":{"openalex":"https://openalex.org/W7205002971","doi":"https://doi.org/10.3390/computers15090576"},"language":"en","primary_location":{"id":"doi:10.3390/computers15090576","doi":"https://doi.org/10.3390/computers15090576","is_oa":true,"landing_page_url":"https://doi.org/10.3390/computers15090576","pdf_url":null,"source":{"id":"https://openalex.org/S4210228075","display_name":"Computers","issn_l":"2073-431X","issn":["2073-431X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","norway-1","poland-20","russia-white-list-2"],"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":"Computers","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.3390/computers15090576","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101431726","display_name":"Yidong Sun","orcid":"https://orcid.org/0009-0004-1633-3392","observed_orcids":["https://orcid.org/0009-0004-1633-3392","https://orcid.org/0000-0003-2005-9459"]},"institutions":[{"id":"https://openalex.org/I4405280973","display_name":"Ma'anshan University","ror":"https://ror.org/03p14ta92","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405280973"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yidong Sun","raw_affiliation_strings":["College of Big Data and Artificial Intelligence, Maanshan University, Maanshan 243000, China"],"raw_orcid":"https://orcid.org/0009-0004-1633-3392","affiliations":[{"raw_affiliation_string":"College of Big Data and Artificial Intelligence, Maanshan University, Maanshan 243000, China","institution_ids":["https://openalex.org/I4405280973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5149073674","display_name":"Dongxu Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405280973","display_name":"Ma'anshan University","ror":"https://ror.org/03p14ta92","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405280973"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongxu Liu","raw_affiliation_strings":["College of Big Data and Artificial Intelligence, Maanshan University, Maanshan 243000, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Big Data and Artificial Intelligence, Maanshan University, Maanshan 243000, China","institution_ids":["https://openalex.org/I4405280973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100744179","display_name":"Jiale Zhang","orcid":"https://orcid.org/0000-0002-6390-9591","observed_orcids":["https://orcid.org/0000-0002-6390-9591","https://orcid.org/0009-0002-4425-3766","https://orcid.org/0009-0003-1902-0474","https://orcid.org/0009-0005-5914-7909","https://orcid.org/0009-0006-2366-1831"]},"institutions":[{"id":"https://openalex.org/I4405280973","display_name":"Ma'anshan University","ror":"https://ror.org/03p14ta92","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405280973"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiale Zhang","raw_affiliation_strings":["College of Big Data and Artificial Intelligence, Maanshan University, Maanshan 243000, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Big Data and Artificial Intelligence, Maanshan University, Maanshan 243000, China","institution_ids":["https://openalex.org/I4405280973"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101775798","display_name":"Youcheng Wang","orcid":"https://orcid.org/0000-0001-8199-0373","observed_orcids":["https://orcid.org/0000-0001-8199-0373"]},"institutions":[{"id":"https://openalex.org/I4405280973","display_name":"Ma'anshan University","ror":"https://ror.org/03p14ta92","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405280973"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Youcheng Wang","raw_affiliation_strings":["College of Big Data and Artificial Intelligence, Maanshan University, Maanshan 243000, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Big Data and Artificial Intelligence, Maanshan University, Maanshan 243000, China","institution_ids":["https://openalex.org/I4405280973"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5101431726"],"corresponding_institution_ids":["https://openalex.org/I4405280973"],"apc_list":{"value":1800,"currency":"CHF","value_usd":2172},"apc_paid":{"value":1800,"currency":"CHF","value_usd":2172},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"15","issue":"9","first_page":"576","last_page":"576"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9976000189781189,"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":0.9976000189781189,"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":0.0010999999940395355,"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/T10759","display_name":"Translation Studies and Practices","score":0.0006000000284984708,"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/low-resource-language-translation","display_name":"low-resource translation","score":0.6679999828338623},{"id":"https://openalex.org/keywords/agglutinative-languages","display_name":"agglutinative languages","score":0.875},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"domain adaptation","score":0.48899999260902405},{"id":"https://openalex.org/keywords/syntactic-alignment","display_name":"syntactic alignment","score":0.5680000185966492},{"id":"https://openalex.org/keywords/terminology-normalization","display_name":"terminology normalization","score":0.609000027179718},{"id":"https://openalex.org/keywords/cross-domain-translation","display_name":"cross-domain translation","score":0.35899999737739563}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6966000199317932},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.6618000268936157},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.6401000022888184},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6007999777793884},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.599399983882904},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5681999921798706},{"id":"https://openalex.org/C547195049","wikidata":"https://www.wikidata.org/wiki/Q1725664","display_name":"Terminology","level":2,"score":0.5178999900817871},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5116999745368958},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.49619999527931213},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.492900013923645},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.46540001034736633},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4562000036239624},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4498000144958496},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.33230000734329224},{"id":"https://openalex.org/C80875076","wikidata":"https://www.wikidata.org/wiki/Q171263","display_name":"Agglutinative language","level":3,"score":0.3156000077724457},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.3138999938964844},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.275299996137619},{"id":"https://openalex.org/C143271835","wikidata":"https://www.wikidata.org/wiki/Q254515","display_name":"Similitude","level":2,"score":0.27250000834465027},{"id":"https://openalex.org/C198352243","wikidata":"https://www.wikidata.org/wiki/Q37105","display_name":"Line (geometry)","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25760000944137573}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/computers15090576","doi":"https://doi.org/10.3390/computers15090576","is_oa":true,"landing_page_url":"https://doi.org/10.3390/computers15090576","pdf_url":null,"source":{"id":"https://openalex.org/S4210228075","display_name":"Computers","issn_l":"2073-431X","issn":["2073-431X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","norway-1","poland-20","russia-white-list-2"],"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":"Computers","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:b29070da178942e99ccdecd3632030b0","doi":null,"is_oa":false,"landing_page_url":"https://doaj.org/article/b29070da178942e99ccdecd3632030b0","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,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computers, Vol 15, Iss 9, p 576 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/computers15090576","doi":"https://doi.org/10.3390/computers15090576","is_oa":true,"landing_page_url":"https://doi.org/10.3390/computers15090576","pdf_url":null,"source":{"id":"https://openalex.org/S4210228075","display_name":"Computers","issn_l":"2073-431X","issn":["2073-431X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","norway-1","poland-20","russia-white-list-2"],"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":"Computers","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320326664","display_name":"Anhui Provincial Department of Education","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1793674293","https://openalex.org/W2009847538","https://openalex.org/W2284660317","https://openalex.org/W2760452458","https://openalex.org/W2798362442","https://openalex.org/W2805411799","https://openalex.org/W2886095922","https://openalex.org/W2889326796","https://openalex.org/W2963736842","https://openalex.org/W2970279348","https://openalex.org/W2983040767","https://openalex.org/W3001434439","https://openalex.org/W3069495034","https://openalex.org/W3100268441","https://openalex.org/W3116179216","https://openalex.org/W3174770825","https://openalex.org/W3196290730","https://openalex.org/W4289521458","https://openalex.org/W4296912034","https://openalex.org/W4309674289","https://openalex.org/W4313219504","https://openalex.org/W4378378836","https://openalex.org/W4388087449","https://openalex.org/W4389611346","https://openalex.org/W4392254153","https://openalex.org/W4392408986","https://openalex.org/W4393900804","https://openalex.org/W4396611057","https://openalex.org/W4401984439","https://openalex.org/W4403060965","https://openalex.org/W4405948167","https://openalex.org/W4406171371","https://openalex.org/W4414406404","https://openalex.org/W7159639944"],"related_works":["https://openalex.org/W2040801613","https://openalex.org/W4416236651","https://openalex.org/W3196290730","https://openalex.org/W4413879682","https://openalex.org/W4402402278","https://openalex.org/W4310580060","https://openalex.org/W4405880045","https://openalex.org/W7214287416","https://openalex.org/W3107673274","https://openalex.org/W4297798762"],"abstract_inverted_index":{"Tibetan-to-English":[0],"machine":[1],"translation":[2],"(MT)":[3],"models":[4],"frequently":[5],"falter":[6],"under":[7,87],"extreme":[8],"domain":[9,183],"data":[10],"scarcity,":[11],"often":[12],"producing":[13],"translations":[14],"that":[15,82,135],"violate":[16],"the":[17,51,54],"distinctive":[18],"agglutinative":[19],"rules":[20],"of":[21,57,148,163],"Tibetan":[22,129,181],"and":[23,60,73,150,171],"suffer":[24],"from":[25],"domain-specific":[26],"stylistic":[27,116,172],"mismatches.":[28],"To":[29],"overcome":[30],"these":[31,94],"limitations,":[32],"we":[33],"propose":[34],"Semantic-Syntax":[35],"Prealignment":[36],"(SSPA),":[37],"an":[38,107],"innovative":[39],"corpus":[40],"generation":[41],"framework.":[42],"SSPA":[43,136,143],"constructs":[44],"high-quality":[45],"pseudo-parallel":[46],"pairs":[47],"by":[48,77,154],"explicitly":[49],"minimizing":[50],"deviation":[52],"between":[53],"syntactic-semantic":[55],"profiles":[56],"generated":[58],"samples":[59],"professional":[61,182],"reference":[62],"texts.":[63],"Specifically,":[64],"source-target":[65],"structural":[66,89],"representations":[67],"are":[68],"standardized":[69],"through":[70],"length-unified":[71],"truncation":[72],"terminology":[74],"normalization,":[75],"followed":[76],"a":[78,98,145,158,175],"dual-domain":[79],"alignment":[80],"process":[81],"maximizes":[83],"syntactic":[84],"cosine":[85],"similarity":[86],"rigorous":[88],"constraints.":[90],"We":[91],"further":[92],"augment":[93],"aligned":[95],"frames":[96],"via":[97],"cross-length":[99],"dynamic":[100],"filling":[101],"mechanism,":[102],"which":[103],"is":[104],"integrated":[105],"with":[106,157],"Expectation-over-Transformation":[108],"(EOT)-based":[109],"style":[110],"regularization":[111],"mechanism":[112],"specifically":[113],"adapted":[114],"for":[115,179],"perturbations,":[117],"to":[118],"simulate":[119],"authentic":[120],"linguistic":[121],"variations.":[122],"Extensive":[123],"evaluations":[124],"on":[125],"our":[126],"newly":[127],"constructed":[128],"Medicine-Tibetan":[130],"English":[131],"(TM-TE)":[132],"dataset":[133],"demonstrate":[134],"significantly":[137],"outperforms":[138],"existing":[139],"competitive":[140],"baselines.":[141],"Notably,":[142],"achieves":[144],"BLEU-4":[146,153],"score":[147],"36.2":[149],"improves":[151],"long-sentence":[152],"16.8":[155],"points,":[156],"parser-verified":[159],"grammatical":[160],"compliance":[161],"rate":[162],"96.2%.":[164],"The":[165],"framework":[166],"exhibits":[167],"remarkable":[168],"cross-domain":[169],"adaptability":[170],"consistency,":[173],"offering":[174],"robust,":[176],"versatile":[177],"solution":[178],"low-resource":[180],"MT.":[184]},"counts_by_year":[],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2026-09-02T00:00:00"}