{"id":"https://openalex.org/W3038876298","doi":"https://doi.org/10.1017/s1351324920000364","title":"Linguistic knowledge-based vocabularies for Neural Machine Translation","display_name":"Linguistic knowledge-based vocabularies for Neural Machine Translation","publication_year":2020,"publication_date":"2020-07-02","ids":{"openalex":"https://openalex.org/W3038876298","doi":"https://doi.org/10.1017/s1351324920000364","mag":"3038876298"},"language":"en","primary_location":{"id":"doi:10.1017/s1351324920000364","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s1351324920000364","pdf_url":null,"source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/2117/330835","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042063974","display_name":"No\u00e9 Casas","orcid":"https://orcid.org/0000-0002-0248-899X"},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Noe Casas","raw_affiliation_strings":["TALP Research Center, Universitat Polit\u00e8cnica de Catalunya"],"raw_orcid":"https://orcid.org/0000-0002-0248-899X","affiliations":[{"raw_affiliation_string":"TALP Research Center, Universitat Polit\u00e8cnica de Catalunya","institution_ids":["https://openalex.org/I9617848"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074210163","display_name":"Marta R. Costa\u2010juss\u00e0","orcid":"https://orcid.org/0000-0002-5703-520X"},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Marta R. Costa-juss\u00e0","raw_affiliation_strings":["TALP Research Center, Universitat Polit\u00e8cnica de Catalunya"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TALP Research Center, Universitat Polit\u00e8cnica de Catalunya","institution_ids":["https://openalex.org/I9617848"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004224082","display_name":"Jos\u00e9 A. R. Fonollosa","orcid":"https://orcid.org/0000-0001-9513-7939"},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jos\u00e9 A. R. Fonollosa","raw_affiliation_strings":["TALP Research Center, Universitat Polit\u00e8cnica de Catalunya"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TALP Research Center, Universitat Polit\u00e8cnica de Catalunya","institution_ids":["https://openalex.org/I9617848"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Juan A. Alonso","orcid":null},"institutions":[{"id":"https://openalex.org/I4210131992","display_name":"United Language Group (United States)","ror":"https://ror.org/02zf60h18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210131992"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Juan A. Alonso","raw_affiliation_strings":["Lucy Software, United Language Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lucy Software, United Language Group","institution_ids":["https://openalex.org/I4210131992"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060017136","display_name":"Ram\u00f3n Fanlo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210131992","display_name":"United Language Group (United States)","ror":"https://ror.org/02zf60h18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210131992"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ram\u00f3n Fanlo","raw_affiliation_strings":["Lucy Software, United Language Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lucy Software, United Language Group","institution_ids":["https://openalex.org/I4210131992"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5042063974"],"corresponding_institution_ids":["https://openalex.org/I9617848"],"apc_list":{"value":3160,"currency":"USD","value_usd":3160},"apc_paid":null,"fwci":0.2841,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.67652297,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"27","issue":"4","first_page":"485","last_page":"506"},"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":0.9998999834060669,"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/T13629","display_name":"Text Readability and Simplification","score":0.9869999885559082,"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/computer-science","display_name":"Computer science","score":0.8801829218864441},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.7141001224517822},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6997296810150146},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.6945076584815979},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6500762104988098},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5938121676445007},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5759832859039307},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.554311215877533},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5292196869850159},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.4376758635044098},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.126712828874588}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8801829218864441},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.7141001224517822},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6997296810150146},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6945076584815979},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6500762104988098},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5938121676445007},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5759832859039307},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.554311215877533},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5292196869850159},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.4376758635044098},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.126712828874588},{"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":2,"locations":[{"id":"doi:10.1017/s1351324920000364","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s1351324920000364","pdf_url":null,"source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"},{"id":"pmh:oai:upcommons.upc.edu:2117/330835","is_oa":true,"landing_page_url":"http://hdl.handle.net/2117/330835","pdf_url":null,"source":{"id":"https://openalex.org/S4377196262","display_name":"UPCommons institutional repository (Universitat Polit\u00e8cnica de Catalunya)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9617848","host_organization_name":"Universitat Polit\u00e8cnica de Catalunya","host_organization_lineage":["https://openalex.org/I9617848"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":{"id":"pmh:oai:upcommons.upc.edu:2117/330835","is_oa":true,"landing_page_url":"http://hdl.handle.net/2117/330835","pdf_url":null,"source":{"id":"https://openalex.org/S4377196262","display_name":"UPCommons institutional repository (Universitat Polit\u00e8cnica de Catalunya)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9617848","host_organization_name":"Universitat Polit\u00e8cnica de Catalunya","host_organization_lineage":["https://openalex.org/I9617848"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[{"score":0.4300000071525574,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G8948449039","display_name":"Autonomous Lifelong learnIng intelLigent Systems","funder_award_id":"ANR-17-CHR2-0004","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W194249466","https://openalex.org/W196214544","https://openalex.org/W222053410","https://openalex.org/W287510790","https://openalex.org/W309335912","https://openalex.org/W1489525520","https://openalex.org/W1902237438","https://openalex.org/W1962622193","https://openalex.org/W1981276685","https://openalex.org/W1988759815","https://openalex.org/W2040711288","https://openalex.org/W2101105183","https://openalex.org/W2107878631","https://openalex.org/W2117621558","https://openalex.org/W2123301721","https://openalex.org/W2123442489","https://openalex.org/W2126241965","https://openalex.org/W2133564696","https://openalex.org/W2157331557","https://openalex.org/W2166221226","https://openalex.org/W2171421863","https://openalex.org/W2295097532","https://openalex.org/W2525778437","https://openalex.org/W2579327808","https://openalex.org/W2598912124","https://openalex.org/W2626778328","https://openalex.org/W2757141711","https://openalex.org/W2783181001","https://openalex.org/W2787214743","https://openalex.org/W2795545650","https://openalex.org/W2799266483","https://openalex.org/W2885096223","https://openalex.org/W2949810612","https://openalex.org/W2950133940","https://openalex.org/W2955541912","https://openalex.org/W2962784628","https://openalex.org/W2963099225","https://openalex.org/W2963188492","https://openalex.org/W2963212250","https://openalex.org/W2963324947","https://openalex.org/W2963532001","https://openalex.org/W2963876447","https://openalex.org/W2964308564","https://openalex.org/W3213128363","https://openalex.org/W4229744135","https://openalex.org/W4285719527","https://openalex.org/W6607974698","https://openalex.org/W6747991721","https://openalex.org/W6765485641","https://openalex.org/W6803512716"],"related_works":["https://openalex.org/W2905433371","https://openalex.org/W4390569940","https://openalex.org/W2888392564","https://openalex.org/W4361193272","https://openalex.org/W4310278675","https://openalex.org/W4388422664","https://openalex.org/W2949968076","https://openalex.org/W2935811960","https://openalex.org/W2969407538","https://openalex.org/W2917049097"],"abstract_inverted_index":{"Abstract":[0],"Neural":[1],"Networks":[2],"applied":[3],"to":[4,11,32,47,58,110,145],"Machine":[5],"Translation":[6],"need":[7],"a":[8,16,146],"finite":[9],"vocabulary":[10,92],"express":[12],"textual":[13],"information":[14],"as":[15],"sequence":[17],"of":[18,30,36,44,100,138],"discrete":[19],"tokens.":[20],"The":[21],"currently":[22],"dominant":[23],"subword":[24,101,148],"vocabularies":[25,38,102],"exploit":[26],"statistically-discovered":[27],"common":[28],"parts":[29],"words":[31],"achieve":[33],"the":[34,41,48,56,98,104,113,118,131,133,136],"flexibility":[35],"character-based":[37],"without":[39],"delegating":[40],"whole":[42],"learning":[43,74],"word":[45],"formation":[46],"neural":[49,108],"network.":[50],"However,":[51],"they":[52],"trade":[53],"this":[54,85],"for":[55,130],"inability":[57],"apply":[59],"word-level":[60,105],"token":[61],"associations,":[62,106],"which":[63],"limits":[64],"their":[65,82],"use":[66],"in":[67,121,135],"semantically-rich":[68],"areas":[69],"and":[70,80,103,125],"prevents":[71],"some":[72],"transfer":[73],"approaches":[75,120],"e.g.":[76],"cross-lingual":[77],"pretrained":[78],"embeddings,":[79],"reduces":[81],"interpretability.":[83],"In":[84],"work,":[86],"we":[87],"propose":[88],"new":[89],"hybrid":[90],"linguistically-grounded":[91],"definition":[93],"strategies":[94],"that":[95],"keep":[96],"both":[97,122],"advantages":[99],"enabling":[107],"networks":[109],"profit":[111],"from":[112],"derived":[114],"benefits.":[115],"We":[116],"test":[117],"proposed":[119],"morphologically":[123],"rich":[124],"poor":[126],"languages,":[127],"showing":[128],"that,":[129],"former,":[132],"quality":[134],"translation":[137],"out-of-domain":[139],"texts":[140],"is":[141],"improved":[142],"with":[143],"respect":[144],"strong":[147],"baseline.":[149]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2020-07-10T00:00:00"}