{"id":"https://openalex.org/W4226000821","doi":"https://doi.org/10.1109/snams53716.2021.9732120","title":"Quasi Character-Level Transformers to Improve Neural Machine Translation on Small Datasets","display_name":"Quasi Character-Level Transformers to Improve Neural Machine Translation on Small Datasets","publication_year":2021,"publication_date":"2021-12-06","ids":{"openalex":"https://openalex.org/W4226000821","doi":"https://doi.org/10.1109/snams53716.2021.9732120"},"language":"en","primary_location":{"id":"doi:10.1109/snams53716.2021.9732120","is_oa":false,"landing_page_url":"https://doi.org/10.1109/snams53716.2021.9732120","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 Eighth International Conference on Social Network Analysis, Management and Security (SNAMS)","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/A5044006913","display_name":"Salvador Carri\u00f3n","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Salvador Carri\u00f3n","raw_affiliation_strings":["Universitat Politècnica de València,PRHLT Research Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universitat Politècnica de València,PRHLT Research Center","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020181962","display_name":"Francisco Casacuberta","orcid":"https://orcid.org/0000-0002-8497-5598"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Francisco Casacuberta","raw_affiliation_strings":["Universitat Politècnica de València,PRHLT Research Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universitat Politècnica de València,PRHLT Research Center","institution_ids":[]}]}],"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":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"abs 2011 4006","issue":null,"first_page":"1","last_page":"6"},"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":0.9771000146865845,"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":0.8195704221725464},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.7676158547401428},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7265006303787231},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6957193613052368},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.6358506679534912},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6018776297569275},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5795131325721741},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.42270150780677795},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.420910120010376},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.42036348581314087},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1076589822769165}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8195704221725464},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7676158547401428},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7265006303787231},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6957193613052368},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.6358506679534912},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6018776297569275},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5795131325721741},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.42270150780677795},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.420910120010376},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.42036348581314087},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1076589822769165},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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},{"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/snams53716.2021.9732120","is_oa":false,"landing_page_url":"https://doi.org/10.1109/snams53716.2021.9732120","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 Eighth International Conference on Social Network Analysis, Management and Security (SNAMS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W22168010","https://openalex.org/W23305027","https://openalex.org/W36903255","https://openalex.org/W46679369","https://openalex.org/W630532510","https://openalex.org/W1902237438","https://openalex.org/W1968594024","https://openalex.org/W2048967369","https://openalex.org/W2064675550","https://openalex.org/W2095705004","https://openalex.org/W2101105183","https://openalex.org/W2115081467","https://openalex.org/W2116599427","https://openalex.org/W2124807415","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2136016850","https://openalex.org/W2149327368","https://openalex.org/W2152790380","https://openalex.org/W2157331557","https://openalex.org/W2163605009","https://openalex.org/W2170716095","https://openalex.org/W2184135559","https://openalex.org/W2250342921","https://openalex.org/W2512924740","https://openalex.org/W2525778437","https://openalex.org/W2575814162","https://openalex.org/W2613904329","https://openalex.org/W2903193068","https://openalex.org/W2933138175","https://openalex.org/W2962732637","https://openalex.org/W2962784628","https://openalex.org/W2963250244","https://openalex.org/W2963324947","https://openalex.org/W2963532001","https://openalex.org/W2963909453","https://openalex.org/W2963979492","https://openalex.org/W3089809702","https://openalex.org/W3103182178","https://openalex.org/W3103682594","https://openalex.org/W4385245566","https://openalex.org/W6600880057","https://openalex.org/W6601546654","https://openalex.org/W6601894380","https://openalex.org/W6674330103","https://openalex.org/W6679436768","https://openalex.org/W6681703963","https://openalex.org/W6682948231","https://openalex.org/W6684191040","https://openalex.org/W6685203456","https://openalex.org/W6686282164","https://openalex.org/W6691646088","https://openalex.org/W6727690538","https://openalex.org/W6732423958","https://openalex.org/W6737778391","https://openalex.org/W6739901393","https://openalex.org/W6767250937","https://openalex.org/W6785783668","https://openalex.org/W7051469422"],"related_works":["https://openalex.org/W1997182898","https://openalex.org/W3176018525","https://openalex.org/W2903533908","https://openalex.org/W3026554633","https://openalex.org/W2903810591","https://openalex.org/W4289548192","https://openalex.org/W2888520903","https://openalex.org/W2963499882","https://openalex.org/W2903399267","https://openalex.org/W2949454572"],"abstract_inverted_index":{"In":[0,81],"the":[1,36,49,120],"Neural":[2],"Machine":[3],"Translation":[4],"community,":[5],"it":[6,71],"is":[7,58,72],"a":[8,22,124],"common":[9,73],"practice":[10,70],"to":[11,18,30,74,107],"use":[12,75],"some":[13],"form":[14],"of":[15,24,39,122,128],"subword":[16,25,113],"segmentation":[17],"encode":[19],"words":[20],"as":[21,76,79],"sequence":[23],"units.":[26],"This":[27],"allows":[28],"practitioners":[29],"represent":[31],"their":[32],"entire":[33],"dataset":[34,63],"using":[35],"least":[37],"amount":[38],"tokens,":[40],"thus":[41],"avoiding":[42],"memory":[43],"and":[44,133],"performance-related":[45],"problems":[46],"derived":[47],"from":[48],"full":[50],"wordor":[51],"purely":[52],"character-level":[53,104],"representations.":[54],"Even":[55],"though":[56],"there":[57],"strong":[59],"evidence":[60],"that":[61],"each":[62],"has":[64],"an":[65],"optimal":[66],"vocabulary":[67],"size,":[68],"in":[69],"many":[77],"\u201cwords\u201d":[78],"possible.":[80],"this":[82,87],"work,":[83],"we":[84],"show":[85],"how":[86],"standard":[88],"approach":[89],"might":[90],"be":[91],"counter-productive":[92],"for":[93],"small":[94],"datasets":[95],"or":[96],"low-resource":[97],"environments,":[98],"where":[99],"models":[100,110],"trained":[101],"with":[102,111,130],"quasi":[103],"vocabularies":[105],"seem":[106],"con-sistently":[108],"outperform":[109],"large":[112],"vocabularies.":[114],"Nonetheless,":[115],"these":[116],"improvements":[117],"come":[118],"at":[119],"expense":[121],"requiring":[123],"neural":[125],"architecture":[126],"capable":[127],"dealing":[129],"long":[131],"sequences":[132],"long-term":[134],"dependencies.":[135]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}