{"id":"https://openalex.org/W4402145836","doi":"https://doi.org/10.1007/978-3-031-71112-1_5","title":"Constructing a BPE Tokenization DFA","display_name":"Constructing a BPE Tokenization DFA","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4402145836","doi":"https://doi.org/10.1007/978-3-031-71112-1_5"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-031-71112-1_5","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-71112-1_5","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":"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/A5028862129","display_name":"Martin Berglund","orcid":"https://orcid.org/0000-0002-3692-6994"},"institutions":[{"id":"https://openalex.org/I90267481","display_name":"Ume\u00e5 University","ror":"https://ror.org/05kb8h459","country_code":"SE","type":"education","lineage":["https://openalex.org/I90267481"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Martin Berglund","raw_affiliation_strings":["Department of Computing Science, Ume\u00e5 University, Ume\u00e5, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing Science, Ume\u00e5 University, Ume\u00e5, Sweden","institution_ids":["https://openalex.org/I90267481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5098657757","display_name":"Willeke Martens","orcid":null},"institutions":[{"id":"https://openalex.org/I90267481","display_name":"Ume\u00e5 University","ror":"https://ror.org/05kb8h459","country_code":"SE","type":"education","lineage":["https://openalex.org/I90267481"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Willeke Martens","raw_affiliation_strings":["Department of Computing Science, Ume\u00e5 University, Ume\u00e5, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing Science, Ume\u00e5 University, Ume\u00e5, Sweden","institution_ids":["https://openalex.org/I90267481"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000026394","display_name":"Brink van der Merwe","orcid":"https://orcid.org/0000-0001-5010-9934"},"institutions":[{"id":"https://openalex.org/I26092322","display_name":"Stellenbosch University","ror":"https://ror.org/05bk57929","country_code":"ZA","type":"education","lineage":["https://openalex.org/I26092322"]},{"id":"https://openalex.org/I4210106521","display_name":"National Institute for Theoretical Physics","ror":"https://ror.org/01jgv6w72","country_code":"ZA","type":"facility","lineage":["https://openalex.org/I4210106521"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Brink van der Merwe","raw_affiliation_strings":["Department of Computer Science, Stellenbosch University, Stellenbosch, South Africa","National Institute for Theoretical and Computational Sciences, Stellenbosch, South Africa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Stellenbosch University, Stellenbosch, South Africa","institution_ids":["https://openalex.org/I26092322"]},{"raw_affiliation_string":"National Institute for Theoretical and Computational Sciences, Stellenbosch, South Africa","institution_ids":["https://openalex.org/I4210106521"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5028862129"],"corresponding_institution_ids":["https://openalex.org/I90267481"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.9755,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.76854207,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"66","last_page":"78"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9986000061035156,"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":0.9986000061035156,"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/T10260","display_name":"Software Engineering Research","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10126","display_name":"Logic, programming, and type systems","score":0.9958999752998352,"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":0.8664525151252747},{"id":"https://openalex.org/keywords/lexical-analysis","display_name":"Lexical analysis","score":0.805408239364624},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2944931089878082}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8664525151252747},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.805408239364624},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2944931089878082}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-031-71112-1_5","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-71112-1_5","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/9","display_name":"Industry, innovation and infrastructure","score":0.4000000059604645}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W2962784628","https://openalex.org/W2963250244","https://openalex.org/W4386699927","https://openalex.org/W4400582517"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W4386014872","https://openalex.org/W1847536016","https://openalex.org/W4361193986","https://openalex.org/W3149094754","https://openalex.org/W2148703997","https://openalex.org/W4366851046","https://openalex.org/W3172681236","https://openalex.org/W2033371749"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}
