{"id":"https://openalex.org/W3116396648","doi":"https://doi.org/10.18653/v1/2020.wat-1.21","title":"Inference-only sub-character decomposition improves translation of unseen logographic characters","display_name":"Inference-only sub-character decomposition improves translation of unseen logographic characters","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3116396648","doi":"https://doi.org/10.18653/v1/2020.wat-1.21","mag":"3116396648"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2020.wat-1.21","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.wat-1.21","pdf_url":"https://aclanthology.org/2020.wat-1.21.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th Workshop on Asian Translation","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2020.wat-1.21.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009117409","display_name":"Danielle Saunders","orcid":"https://orcid.org/0000-0002-7943-3102"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Danielle Saunders","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067609856","display_name":"Weston Feely","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weston Feely","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5070594684","display_name":"Bill Byrne","orcid":"https://orcid.org/0000-0003-1896-4492"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bill Byrne","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"170","last_page":"177"},"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":0.9998000264167786,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9926000237464905,"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/character","display_name":"Character (mathematics)","score":0.7944737672805786},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.786203145980835},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6901556253433228},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6358402967453003},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6282615661621094},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5403128266334534},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.509103000164032},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.46152299642562866},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.45553115010261536},{"id":"https://openalex.org/keywords/character-encoding","display_name":"Character encoding","score":0.4351716637611389},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.4242135286331177},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4205205738544464},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.37015604972839355},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11846849322319031},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09397053718566895}],"concepts":[{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.7944737672805786},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.786203145980835},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6901556253433228},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6358402967453003},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6282615661621094},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5403128266334534},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.509103000164032},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.46152299642562866},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.45553115010261536},{"id":"https://openalex.org/C32717103","wikidata":"https://www.wikidata.org/wiki/Q184759","display_name":"Character encoding","level":3,"score":0.4351716637611389},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4242135286331177},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4205205738544464},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.37015604972839355},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11846849322319031},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09397053718566895},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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/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},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2020.wat-1.21","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.wat-1.21","pdf_url":"https://aclanthology.org/2020.wat-1.21.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th Workshop on Asian Translation","raw_type":"proceedings-article"},{"id":"pmh:oai:generic.eprints.org:1249333","is_oa":false,"landing_page_url":"http://publications.eng.cam.ac.uk/1249333/","pdf_url":null,"source":{"id":"https://openalex.org/S4406922847","display_name":"Cambridge University Engineering Department Publications Database","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":{"id":"doi:10.18653/v1/2020.wat-1.21","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.wat-1.21","pdf_url":"https://aclanthology.org/2020.wat-1.21.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th Workshop on Asian Translation","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2071862857","display_name":null,"funder_award_id":"EP/N509620","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G2465893628","display_name":"Peta-5: A National Facility for Petascale Data Intensive Computation and Analytics","funder_award_id":"EP/P020259/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G2867726338","display_name":null,"funder_award_id":"EP/N509620/","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G3129715815","display_name":"DTP 2016-2017 University of Cambridge","funder_award_id":"EP/N509620/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G5258663329","display_name":null,"funder_award_id":"EP/P020259/","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G6655064812","display_name":"DTP - University of Cambridge","funder_award_id":"EP/M508007/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3116396648.pdf","grobid_xml":"https://content.openalex.org/works/W3116396648.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W1594229598","https://openalex.org/W1779700815","https://openalex.org/W2021766268","https://openalex.org/W2576482813","https://openalex.org/W2757141711","https://openalex.org/W2757875349","https://openalex.org/W2774784811","https://openalex.org/W2918362473","https://openalex.org/W2954632230","https://openalex.org/W2962784628","https://openalex.org/W2963223057","https://openalex.org/W2963403868","https://openalex.org/W2963506925","https://openalex.org/W2963532001","https://openalex.org/W2998353611","https://openalex.org/W3204712539"],"related_works":["https://openalex.org/W3011059803","https://openalex.org/W3151736118","https://openalex.org/W4362495644","https://openalex.org/W2055243143","https://openalex.org/W2962780935","https://openalex.org/W4287236333","https://openalex.org/W4387896177","https://openalex.org/W4385557855","https://openalex.org/W2883671469","https://openalex.org/W2728761353"],"abstract_inverted_index":{"Neural":[0],"Machine":[1],"Translation":[2],"(NMT)":[3],"on":[4,111],"logographic":[5,89],"source":[6,82],"languages":[7,47],"struggles":[8],"when":[9],"translating":[10],"'unseen'":[11],"characters,":[12],"which":[13],"never":[14],"appear":[15],"in":[16],"the":[17],"training":[18,29],"data.One":[19],"possible":[20],"approach":[21,34,119],"to":[22,45],"this":[23,33],"problem":[24],"uses":[25],"sub-character":[26,56,94],"decomposition":[27,57,95,112],"for":[28,41,59,64,115],"and":[30,38,61,67,73,101,127],"test":[31,78],"sentences.However,":[32],"involves":[35],"complete":[36,93],"retraining,":[37],"its":[39],"effectiveness":[40],"unseen":[42,88,98,116],"character":[43,99],"translation":[44,124],"non-logographic":[46],"has":[48],"not":[49],"been":[50],"fully":[51],"explored.We":[52],"investigate":[53],"existing":[54],"ideograph-based":[55],"approaches":[58],"Chinese-to-English":[60],"Japanese-to-English":[62],"NMT,":[63],"both":[65],"high-resource":[66],"low-resource":[68],"domains.For":[69],"each":[70],"language":[71],"pair":[72],"domain":[74],"we":[75],"construct":[76],"a":[77,107],"set":[79],"where":[80],"all":[81],"sentences":[83],"contain":[84],"at":[85],"least":[86],"one":[87],"character.We":[90],"find":[91],"that":[92],"often":[96],"harms":[97],"translation,":[100],"gives":[102],"inconsistent":[103],"results":[104],"generally.We":[105],"offer":[106],"simple":[108],"alternative":[109],"based":[110],"before":[113],"inference":[114],"characters":[117],"only.Our":[118],"allows":[120],"flexible":[121],"application,":[122],"achieving":[123],"adequacy":[125],"improvements":[126],"requiring":[128],"no":[129],"additional":[130],"models":[131],"or":[132],"training.":[133]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}