{"id":"https://openalex.org/W4409311790","doi":"https://doi.org/10.1145/3720498","title":"Efficient Algorithms for the Uniform Tokenization Problem","display_name":"Efficient Algorithms for the Uniform Tokenization Problem","publication_year":2025,"publication_date":"2025-04-09","ids":{"openalex":"https://openalex.org/W4409311790","doi":"https://doi.org/10.1145/3720498"},"language":"en","primary_location":{"id":"doi:10.1145/3720498","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3720498","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3720498","source":{"id":"https://openalex.org/S4210216081","display_name":"Proceedings of the ACM on Programming Languages","issn_l":"2475-1421","issn":["2475-1421"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"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 ACM on Programming Languages","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3720498","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068738516","display_name":"Wu Angela Li","orcid":"https://orcid.org/0000-0002-4523-3401"},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Angela W. Li","raw_affiliation_strings":["Rice University, Houston, USA"],"raw_orcid":"https://orcid.org/0000-0002-4523-3401","affiliations":[{"raw_affiliation_string":"Rice University, Houston, USA","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052392314","display_name":"Konstantinos Mamouras","orcid":"https://orcid.org/0000-0003-1209-7738"},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Konstantinos Mamouras","raw_affiliation_strings":["Rice University, Houston, USA"],"raw_orcid":"https://orcid.org/0000-0003-1209-7738","affiliations":[{"raw_affiliation_string":"Rice University, Houston, USA","institution_ids":["https://openalex.org/I74775410"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74775410"],"apc_list":null,"apc_paid":null,"fwci":3.2965,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.91757927,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"9","issue":"OOPSLA1","first_page":"1492","last_page":"1518"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","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"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","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/T11567","display_name":"semigroups and automata theory","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T13664","display_name":"Genome Rearrangement Algorithms","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/lexical-analysis","display_name":"Lexical analysis","score":0.6226401329040527},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5703955888748169},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5253348350524902},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.18911340832710266}],"concepts":[{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.6226401329040527},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5703955888748169},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5253348350524902},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.18911340832710266}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3720498","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3720498","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3720498","source":{"id":"https://openalex.org/S4210216081","display_name":"Proceedings of the ACM on Programming Languages","issn_l":"2475-1421","issn":["2475-1421"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"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 ACM on Programming Languages","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3720498","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3720498","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3720498","source":{"id":"https://openalex.org/S4210216081","display_name":"Proceedings of the ACM on Programming Languages","issn_l":"2475-1421","issn":["2475-1421"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"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 ACM on Programming Languages","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4314078130","display_name":"CAREER: Programming Abstractions and Formal Reasoning for IoT Application Development","funder_award_id":"2340479","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4409311790.pdf","grobid_xml":"https://content.openalex.org/works/W4409311790.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W33792228","https://openalex.org/W35443084","https://openalex.org/W1574255194","https://openalex.org/W2028637393","https://openalex.org/W2029195137","https://openalex.org/W2033393158","https://openalex.org/W2072607050","https://openalex.org/W2156429182","https://openalex.org/W2179349885","https://openalex.org/W2244392201","https://openalex.org/W2249895122","https://openalex.org/W2293231120","https://openalex.org/W2481729626","https://openalex.org/W2572917468","https://openalex.org/W2951386665","https://openalex.org/W3176694602","https://openalex.org/W3182005208","https://openalex.org/W4205786399","https://openalex.org/W4206544982","https://openalex.org/W4213362721","https://openalex.org/W4241108585","https://openalex.org/W4249383943","https://openalex.org/W4251803872","https://openalex.org/W4281667938","https://openalex.org/W4318147776","https://openalex.org/W4362677176","https://openalex.org/W4390604686","https://openalex.org/W4394999076","https://openalex.org/W4399850754","https://openalex.org/W4399851420","https://openalex.org/W4405244595","https://openalex.org/W4406257922","https://openalex.org/W6966541505"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4405003489","https://openalex.org/W4386014872","https://openalex.org/W1847536016","https://openalex.org/W4361193986","https://openalex.org/W3149094754","https://openalex.org/W2148703997","https://openalex.org/W4366851046"],"abstract_inverted_index":{"Tokenization":[0],"(also":[1],"known":[2],"as":[3],"scanning":[4],"or":[5,30],"lexing)":[6],"is":[7],"a":[8],"computational":[9],"task":[10],"that":[11,51,72],"has":[12],"applications":[13],"in":[14,23],"the":[15,37,48,57,60],"lexical":[16],"analysis":[17,27],"of":[18,59,67,76,78],"programs":[19],"during":[20],"compilation":[21],"and":[22,26,39],"data":[24,32,34,41],"extraction":[25],"for":[28,47],"unstructured":[29],"semistructured":[31],"(e.g.,":[33],"represented":[35],"using":[36,64],"JSON":[38],"CSV":[40],"formats).":[42],"We":[43,69],"propose":[44],"two":[45],"algorithms":[46,80],"tokenization":[49,89],"problem":[50],"have":[52],"linear":[53],"time":[54],"complexity":[55],"(in":[56],"length":[58],"input":[61],"text)":[62],"without":[63],"large":[65],"amounts":[66],"memory.":[68],"also":[70],"show":[71],"an":[73],"optimized":[74],"version":[75],"one":[77],"these":[79],"performs":[81],"well":[82],"compared":[83],"to":[84],"prior":[85],"approaches":[86],"on":[87],"practical":[88],"workloads.":[90]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-24T07:32:12.397491","created_date":"2025-10-10T00:00:00"}