{"id":"https://openalex.org/W4412887763","doi":"https://doi.org/10.18653/v1/2025.findings-acl.1151","title":"Splintering Nonconcatenative Languages for Better Tokenization","display_name":"Splintering Nonconcatenative Languages for Better Tokenization","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412887763","doi":"https://doi.org/10.18653/v1/2025.findings-acl.1151"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.1151","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1151","pdf_url":"https://aclanthology.org/2025.findings-acl.1151.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: ACL 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.1151.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119181211","display_name":"Bar Gazit","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bar Gazit","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041361841","display_name":"Shaltiel Shmidman","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shaltiel Shmidman","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013212409","display_name":"Avi Shmidman","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Avi Shmidman","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5008477284","display_name":"Yuval Pinter","orcid":"https://orcid.org/0000-0003-3174-1621"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuval Pinter","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"22405","last_page":"22417"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12029","display_name":"DNA and Biological Computing","score":0.9976999759674072,"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/T12029","display_name":"DNA and Biological Computing","score":0.9976999759674072,"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/T11567","display_name":"semigroups and automata theory","score":0.9940000176429749,"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/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.9811999797821045,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7818400263786316},{"id":"https://openalex.org/keywords/lexical-analysis","display_name":"Lexical analysis","score":0.7460488080978394},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.5963720679283142},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4889167845249176},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33555006980895996}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7818400263786316},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.7460488080978394},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5963720679283142},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4889167845249176},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33555006980895996}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.1151","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1151","pdf_url":"https://aclanthology.org/2025.findings-acl.1151.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: ACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.1151","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1151","pdf_url":"https://aclanthology.org/2025.findings-acl.1151.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: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1861717563","display_name":null,"funder_award_id":"101071829","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320321449","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412887763.pdf","grobid_xml":"https://content.openalex.org/works/W4412887763.grobid-xml"},"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/W4300598845","https://openalex.org/W3204019825","https://openalex.org/W2601638452","https://openalex.org/W2285263069","https://openalex.org/W4376107815","https://openalex.org/W4319309671"],"abstract_inverted_index":{"Common":[0],"subword":[1],"tokenization":[2],"algorithms":[3],"like":[4],"BPE":[5],"and":[6,29,40,88],"UnigramLM":[7],"assume":[8],"that":[9,59],"text":[10,54],"can":[11],"be":[12,70],"split":[13,43],"into":[14,55],"meaningful":[15,66],"units":[16],"by":[17,72],"concatenative":[18],"measures":[19,81],"alone.This":[20],"is":[21,33],"not":[22],"true":[23],"for":[24,100],"languages":[25],"such":[26,62],"as":[27,90,92],"Hebrew":[28],"Arabic,":[30,87],"where":[31,42],"morphology":[32],"encoded":[34],"in":[35,85],"root-template":[36],"patterns,":[37],"or":[38],"Malay":[39],"Georgian,":[41],"affixes":[44],"are":[45],"common.We":[46],"present":[47],"SPLINTER,":[48],"a":[49,56],"pre-processing":[50],"step":[51],"which":[52],"rearranges":[53],"linear":[57],"form":[58],"better":[60],"represents":[61],"nonconcatenative":[63],"morphologies,":[64],"enabling":[65],"contiguous":[67],"segments":[68],"to":[69],"found":[71],"the":[73],"tokenizer.We":[74],"demonstrate":[75],"SPLINTER's":[76],"merit":[77],"using":[78,96],"both":[79],"intrinsic":[80],"evaluating":[82],"token":[83],"vocabularies":[84],"Hebrew,":[86],"Malay;":[89],"well":[91],"on":[93],"downstream":[94],"tasks":[95],"BERT-architecture":[97],"models":[98],"trained":[99],"Hebrew.":[101]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
