{"id":"https://openalex.org/W4412215980","doi":"https://doi.org/10.18653/v1/2024.findings-eacl.9","title":"Where are we Still Split on Tokenization?","display_name":"Where are we Still Split on Tokenization?","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4412215980","doi":"https://doi.org/10.18653/v1/2024.findings-eacl.9"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2024.findings-eacl.9","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.9","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2024","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.18653/v1/2024.findings-eacl.9","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039811894","display_name":"Rob van der Goot","orcid":"https://orcid.org/0009-0003-1999-4156"},"institutions":[{"id":"https://openalex.org/I83467386","display_name":"IT University of Copenhagen","ror":"https://ror.org/02309jg23","country_code":"DK","type":"education","lineage":["https://openalex.org/I83467386"]}],"countries":["DK"],"is_corresponding":true,"raw_author_name":"Rob van der Goot","raw_affiliation_strings":["IT University of Copenhagen, Computer Science, DK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IT University of Copenhagen, Computer Science, DK","institution_ids":["https://openalex.org/I83467386"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5039811894"],"corresponding_institution_ids":["https://openalex.org/I83467386"],"apc_list":null,"apc_paid":null,"fwci":0.19,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.57071785,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"118","last_page":"137"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11041","display_name":"Ubiquitin and proteasome pathways","score":0.05869999900460243,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"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"}},"topics":[{"id":"https://openalex.org/T11041","display_name":"Ubiquitin and proteasome pathways","score":0.05869999900460243,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"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"}},{"id":"https://openalex.org/T12534","display_name":"Protein Degradation and Inhibitors","score":0.0568000003695488,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"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":0.6358351707458496},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.42024242877960205},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.2123786211013794}],"concepts":[{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.6358351707458496},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.42024242877960205},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2123786211013794}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2024.findings-eacl.9","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.9","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2024","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:openaire/debca73d-1cbc-468c-b15f-666b74d5c158","is_oa":true,"landing_page_url":"https://pure.itu.dk/portal/da/publications/debca73d-1cbc-468c-b15f-666b74d5c158","pdf_url":"https://aclanthology.org/2024.findings-eacl.9.pdf","source":{"id":"https://openalex.org/S4377196680","display_name":"IT University Of Copenhagen (IT University of Copenhagen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I83467386","host_organization_name":"IT University of Copenhagen","host_organization_lineage":["https://openalex.org/I83467386"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"van der Goot, R 2024, Where are we Still Split on Tokenization? in Y Graham & M Purver (eds), Findings of the Association for Computational Linguistics: EACL 2024. Association for Computational Linguistics, St. Julian's, Malta, pp. 118-137. < https://aclanthology.org/2024.findings-eacl.9 >","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:pure.atira.dk:publications/debca73d-1cbc-468c-b15f-666b74d5c158","is_oa":true,"landing_page_url":"https://aclanthology.org/2024.findings-eacl.9","pdf_url":null,"source":{"id":"https://openalex.org/S4377196680","display_name":"IT University Of Copenhagen (IT University of Copenhagen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I83467386","host_organization_name":"IT University of Copenhagen","host_organization_lineage":["https://openalex.org/I83467386"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"van der Goot, R 2024, Where are we Still Split on Tokenization? in Y Graham & M Purver (eds), Findings of the Association for Computational Linguistics: EACL 2024. Association for Computational Linguistics, St. Julian's, Malta, pp. 118-137. < https://aclanthology.org/2024.findings-eacl.9 >","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.findings-eacl.9","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.9","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"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":{"Many":[0],"Natural":[1],"Language":[2],"Processing":[3],"(NLP)":[4],"tasks":[5],"are":[6],"labeled":[7],"on":[8,52,56,62,75,86,122],"the":[9,14,20,53,57,98,103],"token":[10],"level,":[11],"forthese":[12],"tasks,":[13],"first":[15],"step":[16,24],"is":[17,25,83,117],"to":[18,28],"identify":[19],"tokens":[21],"(tokenization).":[22],"Becausethis":[23],"often":[26],"considered":[27],"be":[29,106],"a":[30],"solved":[31],"problem,":[32],"gold":[33],"tokenization":[34,58,81],"iscommonly":[35],"assumed.":[36],"In":[37],"this":[38],"paper,":[39],"we":[40],"propose":[41],"an":[42],"efficient":[43],"method":[44],"fortokenization":[45],"with":[46,77],"subword-based":[47],"language":[48],"models,":[49],"and":[50,79,88,100],"reflect":[51],"status":[54],"ofperformance":[55],"task":[59,104],"by":[60],"evaluating":[61],"122":[63],"languages":[64,110],"in":[65,97,126,131],"20different":[66],"scripts.":[67],"We":[68,93],"show":[69],"that":[70,80,95],"our":[71],"proposed":[72],"model":[73],"performs":[74],"par":[76],"thestate-of-the-art,":[78],"performance":[82],"mainly":[84],"dependent":[85],"theamount":[87],"consistency":[89],"of":[90],"annotated":[91],"data.":[92],"conclude":[94],"besidesinconsistencies":[96],"data":[99],"exceptional":[101],"cases":[102],"can":[105],"consideredsolved":[107],"for":[108,111,124],"Latin":[109],"in-dataset":[112],"settings":[113],"(textgreater99.5":[114],"F1).":[115],"However,performance":[116],"0.75":[118],"F1":[119],"point":[120],"lower":[121],"average":[123],"datasets":[125],"other":[127],"scripts":[128],"andperformance":[129],"deteriorates":[130],"cross-dataset":[132],"setups.":[133]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-07-11T00:00:00"}