{"id":"https://openalex.org/W2905510703","doi":"https://doi.org/10.1007/978-3-031-24337-0_38","title":"How Much Does Tokenization Affect Neural Machine Translation?","display_name":"How Much Does Tokenization Affect Neural Machine Translation?","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W2905510703","doi":"https://doi.org/10.1007/978-3-031-24337-0_38","mag":"2905510703"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-031-24337-0_38","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-24337-0_38","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","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/A5103099224","display_name":"Miguel Domingo","orcid":"https://orcid.org/0000-0002-7910-4536"},"institutions":[{"id":"https://openalex.org/I60053951","display_name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","ror":"https://ror.org/01460j859","country_code":"ES","type":"education","lineage":["https://openalex.org/I60053951"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Miguel Domingo","raw_affiliation_strings":["Pattern Recognition and Human Language Technology Research Center, Universitat Polit\u00e8cnica de Val\u00e8ncia, Camino de Vera s/n, 46022, Valencia, Spain"],"affiliations":[{"raw_affiliation_string":"Pattern Recognition and Human Language Technology Research Center, Universitat Polit\u00e8cnica de Val\u00e8ncia, Camino de Vera s/n, 46022, Valencia, Spain","institution_ids":["https://openalex.org/I60053951"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067705953","display_name":"Mercedes Garc\u00eda-Mart\u00ednez","orcid":"https://orcid.org/0000-0001-6565-3449"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mercedes Garc\u00eda-Mart\u00ednez","raw_affiliation_strings":["Pangeanic/B.I Europa PangeaMT Technologies Division, Valencia, Spain"],"affiliations":[{"raw_affiliation_string":"Pangeanic/B.I Europa PangeaMT Technologies Division, Valencia, Spain","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064073996","display_name":"Alexandre Helle","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexandre Helle","raw_affiliation_strings":["Pangeanic/B.I Europa PangeaMT Technologies Division, Valencia, Spain"],"affiliations":[{"raw_affiliation_string":"Pangeanic/B.I Europa PangeaMT Technologies Division, Valencia, Spain","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020181962","display_name":"Francisco Casacuberta","orcid":"https://orcid.org/0000-0002-8497-5598"},"institutions":[{"id":"https://openalex.org/I60053951","display_name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","ror":"https://ror.org/01460j859","country_code":"ES","type":"education","lineage":["https://openalex.org/I60053951"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Francisco Casacuberta","raw_affiliation_strings":["Pattern Recognition and Human Language Technology Research Center, Universitat Polit\u00e8cnica de Val\u00e8ncia, Camino de Vera s/n, 46022, Valencia, Spain"],"affiliations":[{"raw_affiliation_string":"Pattern Recognition and Human Language Technology Research Center, Universitat Polit\u00e8cnica de Val\u00e8ncia, Camino de Vera s/n, 46022, Valencia, Spain","institution_ids":["https://openalex.org/I60053951"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040323504","display_name":"Manuel Garc\u00eda\u2013Herranz","orcid":"https://orcid.org/0000-0002-4252-4975"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Manuel Herranz","raw_affiliation_strings":["Pangeanic/B.I Europa PangeaMT Technologies Division, Valencia, Spain"],"affiliations":[{"raw_affiliation_string":"Pangeanic/B.I Europa PangeaMT Technologies Division, Valencia, Spain","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5103099224"],"corresponding_institution_ids":["https://openalex.org/I60053951"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":8.5318,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.98008878,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"545","last_page":"554"},"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":0.9995999932289124,"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":0.9674000144004822,"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/lexical-analysis","display_name":"Lexical analysis","score":0.9595580101013184},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8721833229064941},{"id":"https://openalex.org/keywords/punctuation","display_name":"Punctuation","score":0.8605712652206421},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7307526469230652},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.6935303211212158},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6460219621658325},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5942017436027527},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5329820513725281},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.4719468951225281},{"id":"https://openalex.org/keywords/lemmatisation","display_name":"Lemmatisation","score":0.46026426553726196},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3713180422782898},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.22377058863639832}],"concepts":[{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.9595580101013184},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8721833229064941},{"id":"https://openalex.org/C540372491","wikidata":"https://www.wikidata.org/wiki/Q82622","display_name":"Punctuation","level":2,"score":0.8605712652206421},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7307526469230652},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6935303211212158},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6460219621658325},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5942017436027527},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5329820513725281},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4719468951225281},{"id":"https://openalex.org/C161831844","wikidata":"https://www.wikidata.org/wiki/Q2554325","display_name":"Lemmatisation","level":2,"score":0.46026426553726196},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3713180422782898},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.22377058863639832},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-031-24337-0_38","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-24337-0_38","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.800000011920929,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W61894391","https://openalex.org/W222053410","https://openalex.org/W1522301498","https://openalex.org/W1889624880","https://openalex.org/W2064675550","https://openalex.org/W2101105183","https://openalex.org/W2124807415","https://openalex.org/W2130942839","https://openalex.org/W2131774270","https://openalex.org/W2132248251","https://openalex.org/W2149327368","https://openalex.org/W2151197196","https://openalex.org/W2162465526","https://openalex.org/W2164766438","https://openalex.org/W2170464899","https://openalex.org/W2525778437","https://openalex.org/W2594990650","https://openalex.org/W2739602161","https://openalex.org/W2757041753","https://openalex.org/W2952564229","https://openalex.org/W2962784628","https://openalex.org/W2963212250","https://openalex.org/W2963979492","https://openalex.org/W2964308564"],"related_works":["https://openalex.org/W2151197196","https://openalex.org/W2574640638","https://openalex.org/W2202496758","https://openalex.org/W3089211180","https://openalex.org/W2973955309","https://openalex.org/W3034646373","https://openalex.org/W4308083916","https://openalex.org/W2969595679","https://openalex.org/W4382120354","https://openalex.org/W4387484878"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3}],"updated_date":"2026-02-06T02:01:19.302388","created_date":"2025-10-10T00:00:00"}
