{"id":"https://openalex.org/W3156662045","doi":"https://doi.org/10.1145/3431727","title":"Using Sub-character Level Information for Neural Machine Translation of Logographic Languages","display_name":"Using Sub-character Level Information for Neural Machine Translation of Logographic Languages","publication_year":2021,"publication_date":"2021-03-31","ids":{"openalex":"https://openalex.org/W3156662045","doi":"https://doi.org/10.1145/3431727","mag":"3156662045"},"language":"en","primary_location":{"id":"doi:10.1145/3431727","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3431727","pdf_url":null,"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,"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"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3431727","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039366457","display_name":"Longtu Zhang","orcid":"https://orcid.org/0000-0002-2392-9192"},"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":"Longtu Zhang","raw_affiliation_strings":["Tokyo Metropolitan University, Hino, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0002-2392-9192","affiliations":[{"raw_affiliation_string":"Tokyo Metropolitan University, Hino, Tokyo, Japan","institution_ids":["https://openalex.org/I69740276"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061931124","display_name":"Mamoru Komachi","orcid":"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, Hino, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Metropolitan University, Hino, Tokyo, Japan","institution_ids":["https://openalex.org/I69740276"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I69740276"],"apc_list":null,"apc_paid":null,"fwci":1.0919,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.81108559,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"20","issue":"2","first_page":"1","last_page":"15"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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":1.0,"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":0.9988999962806702,"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":0.9965999722480774,"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":0.8179908394813538},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.780844509601593},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6936851739883423},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6146526336669922},{"id":"https://openalex.org/keywords/writing-system","display_name":"Writing system","score":0.6113060712814331},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5207759737968445},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4977295696735382},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.4809412360191345},{"id":"https://openalex.org/keywords/kanji","display_name":"Kanji","score":0.47733622789382935},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.47173964977264404},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4504554867744446},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.4365479350090027},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.37046781182289124},{"id":"https://openalex.org/keywords/chinese-characters","display_name":"Chinese characters","score":0.3536503314971924},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3363206386566162},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.08397981524467468}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8179908394813538},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.780844509601593},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6936851739883423},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6146526336669922},{"id":"https://openalex.org/C78148190","wikidata":"https://www.wikidata.org/wiki/Q8192","display_name":"Writing system","level":2,"score":0.6113060712814331},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5207759737968445},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4977295696735382},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.4809412360191345},{"id":"https://openalex.org/C83535845","wikidata":"https://www.wikidata.org/wiki/Q82772","display_name":"Kanji","level":3,"score":0.47733622789382935},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.47173964977264404},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4504554867744446},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.4365479350090027},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37046781182289124},{"id":"https://openalex.org/C2781051154","wikidata":"https://www.wikidata.org/wiki/Q8201","display_name":"Chinese characters","level":2,"score":0.3536503314971924},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3363206386566162},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.08397981524467468},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3431727","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3431727","pdf_url":null,"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,"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:10.1145/3431727","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3431727","pdf_url":null,"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,"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":[{"score":0.8299999833106995,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"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"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1521626219","https://openalex.org/W2064675550","https://openalex.org/W2157331557","https://openalex.org/W2251131401","https://openalex.org/W2342814244","https://openalex.org/W2531638282","https://openalex.org/W2883691341","https://openalex.org/W2922349260","https://openalex.org/W2933138175","https://openalex.org/W2962784628","https://openalex.org/W2963206679","https://openalex.org/W2963223057","https://openalex.org/W2963887123","https://openalex.org/W2964110616"],"related_works":["https://openalex.org/W3107474891","https://openalex.org/W3116857254","https://openalex.org/W3119899169","https://openalex.org/W3198474835","https://openalex.org/W3204726280","https://openalex.org/W2368651715","https://openalex.org/W3120942684","https://openalex.org/W4297801452","https://openalex.org/W2533485883","https://openalex.org/W3156662045"],"abstract_inverted_index":{"Logographic":[0],"and":[1,51,77,98,103,110,156],"alphabetic":[2],"languages":[3],"(e.g.,":[4],"Chinese":[5,50],"vs.":[6],"English)":[7],"have":[8],"different":[9],"writing":[10,18],"systems":[11,73],"linguistically.":[12],"Languages":[13],"belonging":[14],"to":[15,29,150],"the":[16,46,63,69,83,89,116,127,133,159],"same":[17],"system":[19],"usually":[20,120],"exhibit":[21],"more":[22,60],"sharing":[23],"information,":[24],"which":[25],"can":[26,86,130,147],"be":[27,148],"used":[28],"facilitate":[30],"natural":[31,162],"language":[32,95,105,163],"processing":[33,164],"tasks":[34],"such":[35],"as":[36,115],"neural":[37],"machine":[38],"translation":[39],"(NMT).":[40],"This":[41],"article":[42],"takes":[43],"advantage":[44],"of":[45,71,92,135,161],"logographic":[47],"characters":[48,66],"in":[49,68,74,107],"Japanese":[52],"by":[53],"decomposing":[54],"them":[55],"into":[56],"smaller":[57],"units,":[58],"thus":[59],"optimally":[61],"utilizing":[62],"information":[64],"these":[65,136],"share":[67,153],"training":[70],"NMT":[72,90,112],"both":[75,93,108],"encoding":[76],"decoding":[78],"processes.":[79],"Experiments":[80],"show":[81],"that":[82],"proposed":[84],"method":[85],"robustly":[87],"improve":[88,158],"performance":[91,160],"\u201clogographic\u201d":[94],"pairs":[96,106],"(JA\u2013ZH)":[97],"\u201clogographic":[99],"+":[100],"alphabetic\u201d":[101],"(JA\u2013EN":[102],"ZH\u2013EN)":[104],"supervised":[109],"unsupervised":[111],"scenarios.":[113],"Moreover,":[114],"decomposed":[117],"sequences":[118],"are":[119],"very":[121],"long,":[122],"extra":[123],"position":[124],"features":[125,146],"for":[126],"transformer":[128],"encoder":[129],"help":[131],"with":[132],"modeling":[134],"long":[137],"sequences.":[138],"The":[139],"results":[140],"also":[141],"indicate":[142],"that,":[143],"theoretically,":[144],"linguistic":[145],"manipulated":[149],"obtain":[151],"higher":[152],"token":[154],"rates":[155],"further":[157],"systems.":[165]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}