{"id":"https://openalex.org/W4417239904","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.241","title":"Pretraining Language Models for Diachronic Linguistic Change Discovery","display_name":"Pretraining Language Models for Diachronic Linguistic Change Discovery","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4417239904","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.241"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.findings-eacl.241","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.241","pdf_url":"https://aclanthology.org/2026.findings-eacl.241.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":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-eacl.241.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5097605582","display_name":"Elisabeth Fittschen","orcid":"https://orcid.org/0009-0001-3702-671X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Elisabeth Fittschen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053622179","display_name":"Sabrina Li","orcid":"https://orcid.org/0000-0003-2145-4493"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sabrina Xin Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046184426","display_name":"Tom Lippincott","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tom Lippincott","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040286212","display_name":"Leshem Choshen","orcid":"https://orcid.org/0000-0002-0085-6496"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Leshem Choshen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5093817186","display_name":"Craig Messner","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Craig Messner","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":"4627","last_page":"4642"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12090","display_name":"Language and cultural evolution","score":0.6377999782562256,"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"}},"topics":[{"id":"https://openalex.org/T12090","display_name":"Language and cultural evolution","score":0.6377999782562256,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.22220000624656677,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.02419999986886978,"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/pipeline","display_name":"Pipeline (software)","score":0.694599986076355},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.6333000063896179},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6035000085830688},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5906999707221985},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.48910000920295715},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4788999855518341},{"id":"https://openalex.org/keywords/extension","display_name":"Extension (predicate logic)","score":0.46140000224113464},{"id":"https://openalex.org/keywords/computational-linguistics","display_name":"Computational linguistics","score":0.4316999912261963}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7630000114440918},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.694599986076355},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.6333000063896179},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6035000085830688},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5906999707221985},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5726000070571899},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5716000199317932},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.48910000920295715},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4788999855518341},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.46140000224113464},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.4316999912261963},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.4074000120162964},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.3596000075340271},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3156000077724457},{"id":"https://openalex.org/C153578388","wikidata":"https://www.wikidata.org/wiki/Q351625","display_name":"Theoretical linguistics","level":2,"score":0.31470000743865967},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3102000057697296},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2757999897003174},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2606000006198883}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/2026.findings-eacl.241","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.241","pdf_url":"https://aclanthology.org/2026.findings-eacl.241.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:arXiv.org:2504.05523","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.05523","pdf_url":"https://arxiv.org/pdf/2504.05523","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":null,"raw_type":"text"},{"id":"pmh:doi:10.48550/arxiv.2504.05523","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","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":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2504.05523","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2504.05523","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-eacl.241","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.241","pdf_url":"https://aclanthology.org/2026.findings-eacl.241.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":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417239904.pdf","grobid_xml":"https://content.openalex.org/works/W4417239904.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2,59,78],"(LLMs)":[3],"are":[4,84],"increasingly":[5],"used":[6],"as":[7],"knowledge":[8],"discovery":[9],"tools.Humanistic":[10],"disciplines":[11],"like":[12,35],"historical":[13,65,81],"linguistics":[14],"and":[15,83,107,114,127],"literary":[16],"studies":[17],"have":[18],"shown":[19],"interest":[20],"in":[21,101],"this":[22],"capability.These":[23],"fields":[24],"often":[25],"construct":[26],"arguments":[27],"on":[28,43],"the":[29,90,99],"basis":[30],"of":[31,49,60,93,111,119,133],"distinctions":[32],"between":[33],"phenomena":[34],"time-period":[36],"or":[37],"genre.Such":[38],"methodological":[39],"investments":[40],"complicate":[41],"reliance":[42],"LLMs":[44],"pretrained":[45],"over":[46,63],"large":[47],"sets":[48],"broadly-collected":[50],"data.We":[51,73],"show":[52],"that":[53,75,122],"efficient":[54,87],"pretraining":[55],"techniques":[56],"produce":[57],"useful":[58],"semantic":[61],"change":[62],"modest":[64],"corpora":[66],"without":[67],"allowing":[68],"potential":[69],"contamination":[70],"from":[71],"anachronistic":[72],"verify":[74],"these":[76],"trained-from-scratch":[77],"better":[79],"respect":[80],"divisions":[82],"more":[85],"computationally":[86],"compared":[88],"to":[89,129],"standard":[91],"approach":[92,121],"fine-tuning":[94],"an":[95],"existing":[96],"LLM.We":[97],"compare":[98],"trade-offs":[100],"general":[102],"linguistic":[103,112],"fluency":[104],"versus":[105],"detecting":[106],"characterizing":[108],"various":[109],"forms":[110],"change,":[113],"provide":[115],"a":[116,130],"pipeline":[117],"implementation":[118],"our":[120],"can":[123],"be":[124],"readily":[125],"adapted":[126],"applied":[128],"wide":[131],"range":[132],"diachronic":[134],"phenomena.":[135]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}