{"id":"https://openalex.org/W7140143811","doi":"https://doi.org/10.18653/v1/2026.eacl-long.270","title":"Contextual morphologically-guided tokenization for Latin encoder models","display_name":"Contextual morphologically-guided tokenization for Latin encoder models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140143811","doi":"https://doi.org/10.18653/v1/2026.eacl-long.270"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.eacl-long.270","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.270","pdf_url":"https://aclanthology.org/2026.eacl-long.270.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":"Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.eacl-long.270.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130382353","display_name":"Marisa Hudspeth","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marisa Hudspeth","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130343409","display_name":"Patrick J. Burns","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Patrick J. Burns","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5124500019","display_name":"Brendan O'Connor","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Brendan O'Connor","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"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":0.40179979,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5761","last_page":"5775"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.7580000162124634,"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":0.7580000162124634,"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/T12090","display_name":"Language and cultural evolution","score":0.025299999862909317,"subfield":{"id":"https://openalex.org/subfields/3316","display_name":"Cultural Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.02280000038444996,"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/encoder","display_name":"Encoder","score":0.4586000144481659},{"id":"https://openalex.org/keywords/lexical-analysis","display_name":"Lexical analysis","score":0.33660000562667847},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.31139999628067017},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.2574999928474426}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7254999876022339},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5935999751091003},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5364999771118164},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4586000144481659},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.33660000562667847},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.31139999628067017},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2849999964237213},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2766000032424927},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2574999928474426},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.23659999668598175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.eacl-long.270","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.270","pdf_url":"https://aclanthology.org/2026.eacl-long.270.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":"Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.eacl-long.270","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.270","pdf_url":"https://aclanthology.org/2026.eacl-long.270.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":"Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G184176519","display_name":"CAREER: Social Aggregate Measurement from Text","funder_award_id":"1845576","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6671297155","display_name":null,"funder_award_id":"CAREER","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/W7140143811.pdf","grobid_xml":"https://content.openalex.org/works/W7140143811.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Tokenization":[0],"is":[1,62,80],"a":[2,57,149],"critical":[3,84],"component":[4],"of":[5,66,73,87,108,121,143],"language":[6,60,89,126],"model":[7],"pretraining,":[8],"yet":[9],"standard":[10],"tokenization":[11,43,54,94],"methods":[12],"often":[13,81],"prioritize":[14],"informationtheoretical":[15],"goals":[16,26],"like":[17,27],"high":[18],"compression":[19],"and":[20,141],"low":[21],"fertility":[22],"rather":[23],"than":[24],"linguistic":[25,122,144],"morphological":[28],"alignment.In":[29],"fact,":[30],"they":[31],"have":[32],"been":[33],"shown":[34],"to":[35,124,152],"be":[36],"suboptimal":[37],"for":[38,55,106,128],"morphologically":[39,58,129],"rich":[40,59],"languages,":[41],"where":[42],"quality":[44],"directly":[45],"impacts":[46],"downstream":[47,100],"performance.In":[48],"this":[49],"work,":[50],"we":[51],"investigate":[52],"morphologicallyaware":[53],"Latin,":[56],"that":[61,79,92,134],"medium-resource":[63],"in":[64,71,85],"terms":[65,72],"pretraining":[67,137],"data,":[68,138],"but":[69,83],"high-resource":[70],"curated":[74],"lexical":[75],"resources":[76,123,145],"-a":[77],"distinction":[78],"overlooked":[82],"discussions":[86],"low-resource":[88,132],"modeling.We":[90],"find":[91],"morphologically-guided":[93],"improves":[95],"overall":[96],"performance":[97],"on":[98],"four":[99],"tasks.Performance":[101],"gains":[102],"are":[103],"most":[104],"pronounced":[105],"out":[107],"domain":[109],"texts,":[110],"highlighting":[111],"our":[112],"models'":[113],"improved":[114],"generalization":[115],"ability.Our":[116],"findings":[117],"demonstrate":[118],"the":[119,139],"utility":[120],"improve":[125,153],"modeling":[127],"complex":[130],"languages.For":[131],"languages":[133],"lack":[135],"large-scale":[136],"development":[140],"incorporation":[142],"can":[146],"serve":[147],"as":[148],"feasible":[150],"alternative":[151],"LM":[154],"performance.":[155],"1":[156]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-24T00:00:00"}