{"id":"https://openalex.org/W7140145436","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.211","title":"ReBPE: Iteratively Improving the Internal Structure of a Structured Tokeniser by Mining its Internal Structure","display_name":"ReBPE: Iteratively Improving the Internal Structure of a Structured Tokeniser by Mining its Internal Structure","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140145436","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.211"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-eacl.211","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.211","pdf_url":"https://aclanthology.org/2026.findings-eacl.211.pdf","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 2026","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-eacl.211.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130400120","display_name":"Thomas Bauwens","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thomas Bauwens","raw_affiliation_strings":["Department of Computer Science , KU Leuven"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , KU Leuven","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5130338733","display_name":"Miryam de Lhoneux","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Miryam de Lhoneux","raw_affiliation_strings":["Department of Computer Science , KU Leuven"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , KU Leuven","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31966631,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4075","last_page":"4090"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12482","display_name":"Tunneling and Rock Mechanics","score":0.033900000154972076,"subfield":{"id":"https://openalex.org/subfields/2205","display_name":"Civil and Structural Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12482","display_name":"Tunneling and Rock Mechanics","score":0.033900000154972076,"subfield":{"id":"https://openalex.org/subfields/2205","display_name":"Civil and Structural Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12282","display_name":"Mineral Processing and Grinding","score":0.020899999886751175,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12326","display_name":"Network Packet Processing and Optimization","score":0.01759999990463257,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/component","display_name":"Component (thermodynamics)","score":0.29750001430511475},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.27950000762939453},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.2759000062942505},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.2583000063896179},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.25519999861717224}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4912000000476837},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30799999833106995},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.29750001430511475},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.27950000762939453},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.2759000062942505},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2621999979019165},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2583000063896179},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2547999918460846},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.25200000405311584}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2026.findings-eacl.211","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.211","pdf_url":"https://aclanthology.org/2026.findings-eacl.211.pdf","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 2026","raw_type":"proceedings-article"},{"id":"pmh:oai:lirias2repo.kuleuven.be:20.500.12942/786051","is_oa":true,"landing_page_url":"https://lirias.kuleuven.be/handle/20.500.12942/786051","pdf_url":"https://lirias.kuleuven.be/retrieve/73515320-3d78-4029-a171-213027ffc976","source":{"id":"https://openalex.org/S7407055369","display_name":"Lirias","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"19th Conference of the European Chapter of the Association for Computational Linguistics, Rabat, Morocco","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-eacl.211","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.211","pdf_url":"https://aclanthology.org/2026.findings-eacl.211.pdf","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 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322308","display_name":"KU Leuven","ror":"https://ror.org/05f950310"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140145436.pdf","grobid_xml":"https://content.openalex.org/works/W7140145436.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"work":[1],"has":[2],"explored":[3],"pruning":[4,64],"merges":[5,18,50,80],"from":[6],"BPE":[7,25,98],"subword":[8],"tokenisers":[9],"using":[10],"corpus":[11],"data":[12,30],"as":[13,44],"a":[14,24,28,45,73,96],"signal":[15],"for":[16],"which":[17,101],"to":[19,47,60],"prune.We":[20],"argue":[21],"that":[22,52,77],"because":[23],"tokeniser":[26],"contains":[27],"rich":[29],"structure":[31],"on":[32,107,120],"top":[33],"of":[34,62],"its":[35,49],"vocabulary":[36],"set,":[37],"this":[38,58],"in":[39,110],"itself":[40],"can":[41],"be":[42],"used":[43],"guide":[46],"modify":[48],"such":[51],"segmentations":[53],"become":[54],"more":[55],"desirable.We":[56],"apply":[57],"argument":[59],"one":[61],"those":[63],"algorithms,":[65],"BPE-knockout":[66,105],"(Bauwens":[67],"and":[68],"Delobelle,":[69],"2024),":[70],"by":[71,81,86,115],"introducing":[72],"new":[74,79,97],"reification":[75],"step":[76],"suggests":[78],"inspecting":[82],"the":[83,103],"effects":[84],"left":[85],"pruning.By":[87],"alternating":[88],"both":[89],"processes":[90],"iteratively":[91],"until":[92],"convergence,":[93],"we":[94],"get":[95],"tokeniser,":[99],"ReBPE,":[100],"outperforms":[102],"original":[104],"algorithm":[106],"morphological":[108],"alignment":[109],"all":[111],"14":[112],"languages":[113],"tested":[114],"over":[116],"11%":[117],"F":[118],"1":[119],"average.":[121]},"counts_by_year":[],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2026-03-24T00:00:00"}