{"id":"https://openalex.org/W4384828005","doi":"https://doi.org/10.1145/3608947","title":"North Korean Neural Machine Translation through South Korean Resources","display_name":"North Korean Neural Machine Translation through South Korean Resources","publication_year":2023,"publication_date":"2023-07-19","ids":{"openalex":"https://openalex.org/W4384828005","doi":"https://doi.org/10.1145/3608947"},"language":"en","primary_location":{"id":"doi:10.1145/3608947","doi":"https://doi.org/10.1145/3608947","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3608947","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3608947","source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["ccf-c","cwts-core","dongbi-d","jufo-1","norway-1","poland-70","russia-white-list-2"],"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3608947","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066853717","display_name":"Hwichan Kim","orcid":"https://orcid.org/0009-0007-3146-4085","observed_orcids":["https://orcid.org/0009-0007-3146-4085"]},"institutions":[{"id":"https://openalex.org/I69740276","display_name":"Tokyo Metropolitan University","ror":"https://ror.org/00ws30h19","country_code":"JP","type":"education","lineage":["https://openalex.org/I69740276"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hwichan Kim","raw_affiliation_strings":["Tokyo Metropolitan University, Japan"],"raw_orcid":"https://orcid.org/0009-0007-3146-4085","affiliations":[{"raw_affiliation_string":"Tokyo Metropolitan University, Japan","institution_ids":["https://openalex.org/I69740276"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014468179","display_name":"Tosho Hirasawa","orcid":"https://orcid.org/0000-0003-4657-8214","observed_orcids":["https://orcid.org/0000-0003-4657-8214"]},"institutions":[{"id":"https://openalex.org/I69740276","display_name":"Tokyo Metropolitan University","ror":"https://ror.org/00ws30h19","country_code":"JP","type":"education","lineage":["https://openalex.org/I69740276"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hirasawa Tosho","raw_affiliation_strings":["Tokyo Metropolitan University, Japan"],"raw_orcid":"https://orcid.org/0000-0003-4657-8214","affiliations":[{"raw_affiliation_string":"Tokyo Metropolitan University, Japan","institution_ids":["https://openalex.org/I69740276"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070498298","display_name":"Sangwhan Moon","orcid":"https://orcid.org/0000-0001-9033-9304","observed_orcids":["https://orcid.org/0000-0001-9033-9304"]},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698","https://openalex.org/I4400009020"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sangwhan Moon","raw_affiliation_strings":["Tokyo Institute of Technology, Japan"],"raw_orcid":"https://orcid.org/0000-0001-9033-9304","affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066940046","display_name":"Naoaki Okazaki","orcid":"https://orcid.org/0000-0001-7635-6175","observed_orcids":["https://orcid.org/0000-0001-7635-6175"]},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698","https://openalex.org/I4400009020"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Naoaki Okazaki","raw_affiliation_strings":["Tokyo Institute of Technology, Japan"],"raw_orcid":"https://orcid.org/0000-0001-7635-6175","affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061931124","display_name":"Mamoru Komachi","orcid":"https://orcid.org/0000-0003-1166-1739","observed_orcids":["https://orcid.org/0000-0003-1166-1739"]},"institutions":[{"id":"https://openalex.org/I69740276","display_name":"Tokyo Metropolitan University","ror":"https://ror.org/00ws30h19","country_code":"JP","type":"education","lineage":["https://openalex.org/I69740276"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Mamoru Komachi","raw_affiliation_strings":["Tokyo Metropolitan University, Japan"],"raw_orcid":"https://orcid.org/0000-0003-1166-1739","affiliations":[{"raw_affiliation_string":"Tokyo Metropolitan University, Japan","institution_ids":["https://openalex.org/I69740276"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2079,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.44789431,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":95},"biblio":{"volume":"22","issue":"9","first_page":"1","last_page":"22"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9940999746322632,"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":0.9940999746322632,"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":0.003100000089034438,"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":0.0013000000035390258,"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/north-korean-language","display_name":"North Korean language","score":0.824999988079071},{"id":"https://openalex.org/keywords/neural-machine-translation","display_name":"neural machine translation","score":0.9160000085830688},{"id":"https://openalex.org/keywords/korean-language","display_name":"Korean language","score":0.6290000081062317},{"id":"https://openalex.org/keywords/parallel-corpus-construction","display_name":"parallel corpus construction","score":0.8090000152587891},{"id":"https://openalex.org/keywords/comparable-corpora","display_name":"comparable corpora","score":0.9279999732971191},{"id":"https://openalex.org/keywords/sentence-alignment","display_name":"sentence alignment","score":0.8999999761581421},{"id":"https://openalex.org/keywords/low-resource-language-processing","display_name":"low-resource language processing","score":0.5979999899864197},{"id":"https://openalex.org/keywords/pre-trained-model-transfer","display_name":"pre-trained model transfer","score":0.5379999876022339}],"concepts":[{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.778354287147522},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7726068496704102},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6302791833877563},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6238131523132324},{"id":"https://openalex.org/C2994326100","wikidata":"https://www.wikidata.org/wiki/Q9176","display_name":"Korean language","level":2,"score":0.5568138360977173},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.535487949848175},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.5198755264282227},{"id":"https://openalex.org/C2985367798","wikidata":"https://www.wikidata.org/wiki/Q1346592","display_name":"Parallel corpora","level":3,"score":0.48134860396385193},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.4474947154521942},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1932869851589203},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3608947","doi":"https://doi.org/10.1145/3608947","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3608947","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3608947","source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["ccf-c","cwts-core","dongbi-d","jufo-1","norway-1","poland-70","russia-white-list-2"],"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3608947","doi":"https://doi.org/10.1145/3608947","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3608947","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3608947","source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["ccf-c","cwts-core","dongbi-d","jufo-1","norway-1","poland-70","russia-white-list-2"],"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1251039223","display_name":"Compositionality and Interpretation of Word Embeddings","funder_award_id":"19K12099","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G8894170145","display_name":null,"funder_award_id":"JPMJFS2139","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4384828005.pdf","grobid_xml":"https://content.openalex.org/works/W4384828005.grobid-xml"},"referenced_works_count":49,"referenced_works":["https://openalex.org/W1489181569","https://openalex.org/W1524281572","https://openalex.org/W1538021842","https://openalex.org/W2065165780","https://openalex.org/W2084413241","https://openalex.org/W2088612258","https://openalex.org/W2117652747","https://openalex.org/W2166098990","https://openalex.org/W2168929382","https://openalex.org/W2337363174","https://openalex.org/W2339995566","https://openalex.org/W2507478797","https://openalex.org/W2511852057","https://openalex.org/W2512814023","https://openalex.org/W2513660799","https://openalex.org/W2514208185","https://openalex.org/W2517504876","https://openalex.org/W2531207078","https://openalex.org/W2576742006","https://openalex.org/W2607106700","https://openalex.org/W2616647696","https://openalex.org/W2741788241","https://openalex.org/W2742155240","https://openalex.org/W2751193242","https://openalex.org/W2759088880","https://openalex.org/W2798389157","https://openalex.org/W2798935874","https://openalex.org/W2885185669","https://openalex.org/W2899182573","https://openalex.org/W2899337869","https://openalex.org/W2905749056","https://openalex.org/W2916009164","https://openalex.org/W2916835973","https://openalex.org/W2933138175","https://openalex.org/W2950940239","https://openalex.org/W2963777589","https://openalex.org/W2971296908","https://openalex.org/W2975831374","https://openalex.org/W2982399380","https://openalex.org/W3027035904","https://openalex.org/W3034407863","https://openalex.org/W3035219095","https://openalex.org/W3037536473","https://openalex.org/W3093421262","https://openalex.org/W3106144205","https://openalex.org/W3159892921","https://openalex.org/W3166316189","https://openalex.org/W3177765786","https://openalex.org/W3199004261"],"related_works":["https://openalex.org/W4226064081","https://openalex.org/W3037460861","https://openalex.org/W4387369068","https://openalex.org/W7160239500","https://openalex.org/W3118944279","https://openalex.org/W3192578585","https://openalex.org/W4288018480","https://openalex.org/W2950878926","https://openalex.org/W3213185812","https://openalex.org/W3006000574"],"abstract_inverted_index":{"South":[0,20,128,154],"and":[1,98,121,135,148],"North":[2,41,48,81,111,117,123,168],"Korea":[3],"both":[4],"use":[5,152],"the":[6,28,52,61,101,153,162,167],"Korean":[7,10,21,29,42,49,82,112,118,124,129,155,169],"language.":[8,22],"However,":[9],"natural":[11],"language":[12],"processing":[13],"(NLP)":[14],"research":[15],"has":[16],"mostly":[17],"focused":[18],"on":[19],"Therefore,":[23],"existing":[24],"NLP":[25],"systems":[26],"in":[27],"language,":[30],"such":[31,131],"as":[32,132],"neural":[33],"machine":[34],"translation":[35,125,170],"(NMT)":[36],"systems,":[37],"cannot":[38],"properly":[39],"process":[40],"inputs.":[43],"Training":[44],"a":[45,75,80,86,110,136],"model":[46,84,114],"using":[47,85,115,127],"data":[50,62,97,120,134],"is":[51],"most":[53],"straightforward":[54],"approach":[55],"to":[56,63,78,94,104,151,173],"solving":[57],"this":[58,71],"problem,":[59,72],"but":[60],"train":[64],"NMT":[65,83,113],"models":[66],"are":[67],"insufficient.":[68],"To":[69],"solve":[70],"we":[73,141],"constructed":[74],"parallel":[76,92,119,133],"corpus":[77],"develop":[79],"comparable":[87],"corpus.":[88],"We":[89,108,159],"manually":[90],"aligned":[91,100],"sentences":[93,103],"create":[95,105],"evaluation":[96],"automatically":[99],"remaining":[102],"training":[106],"data.":[107],"trained":[109],"our":[116],"improved":[122],"quality":[126],"resources":[130,156],"pre-trained":[137],"model.":[138],"In":[139],"addition,":[140],"propose":[142],"Korean-specific":[143],"pre-processing":[144,175],"methods,":[145],"character":[146],"tokenization,":[147],"phoneme":[149,163],"decomposition":[150,164],"more":[157],"efficiently.":[158],"demonstrate":[160],"that":[161],"consistently":[165],"improves":[166],"accuracy":[171],"compared":[172],"other":[174],"methods.":[176]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2023-07-21T00:00:00"}