{"id":"https://openalex.org/W4417142393","doi":"https://doi.org/10.63317/2h4yw3wrpuut","title":"Transformer-Enabled Diachronic Analysis of Vedic Sanskrit: Neural Methods for Quantifying Types of Language Change","display_name":"Transformer-Enabled Diachronic Analysis of Vedic Sanskrit: Neural Methods for Quantifying Types of Language Change","publication_year":2026,"publication_date":"2026-04-30","ids":{"openalex":"https://openalex.org/W4417142393","doi":"https://doi.org/10.63317/2h4yw3wrpuut"},"language":null,"primary_location":{"id":"doi:10.63317/2h4yw3wrpuut","is_oa":false,"landing_page_url":"https://doi.org/10.63317/2h4yw3wrpuut","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2512.05364","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047945379","display_name":"Aravind Hariharan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ananth A. Hariharan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5059859009","display_name":"David R. Mortensen","orcid":"https://orcid.org/0000-0002-3927-6851"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David R. Mortensen","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":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00626959,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1044","last_page":"1053"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12090","display_name":"Language and cultural evolution","score":0.9797000288963318,"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":0.9797000288963318,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.0026000000070780516,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.002199999988079071,"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/feature","display_name":"Feature (linguistics)","score":0.5407999753952026},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.46389999985694885},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.447299987077713},{"id":"https://openalex.org/keywords/calibration","display_name":"Calibration","score":0.4018999934196472},{"id":"https://openalex.org/keywords/hybrid-system","display_name":"Hybrid system","score":0.35670000314712524},{"id":"https://openalex.org/keywords/morpheme","display_name":"Morpheme","score":0.34139999747276306},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.33959999680519104},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.3359000086784363}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6342999935150146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5942000150680542},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5407999753952026},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.46389999985694885},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.447299987077713},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4108000099658966},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.4018999934196472},{"id":"https://openalex.org/C50897621","wikidata":"https://www.wikidata.org/wiki/Q2665508","display_name":"Hybrid system","level":2,"score":0.35670000314712524},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34779998660087585},{"id":"https://openalex.org/C165297611","wikidata":"https://www.wikidata.org/wiki/Q43249","display_name":"Morpheme","level":2,"score":0.34139999747276306},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.33959999680519104},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.3359000086784363},{"id":"https://openalex.org/C134121241","wikidata":"https://www.wikidata.org/wiki/Q899301","display_name":"Yield (engineering)","level":2,"score":0.3336000144481659},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.3287000060081482},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C2776095024","wikidata":"https://www.wikidata.org/wiki/Q524648","display_name":"Language change","level":2,"score":0.27639999985694885},{"id":"https://openalex.org/C203595873","wikidata":"https://www.wikidata.org/wiki/Q25389927","display_name":"Change detection","level":2,"score":0.26759999990463257},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.26570001244544983},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.25929999351501465},{"id":"https://openalex.org/C109747225","wikidata":"https://www.wikidata.org/wiki/Q815758","display_name":"Scarcity","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.2565000057220459},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.25290000438690186}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.63317/2h4yw3wrpuut","is_oa":false,"landing_page_url":"https://doi.org/10.63317/2h4yw3wrpuut","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2512.05364","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.05364","pdf_url":"https://arxiv.org/pdf/2512.05364","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2512.05364","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.05364","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"pmh:oai:arXiv.org:2512.05364","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.05364","pdf_url":"https://arxiv.org/pdf/2512.05364","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0],"study":[1],"demonstrates":[2],"how":[3,40],"hybrid":[4,42],"neural-symbolic":[5],"methods":[6,43],"can":[7,44],"yield":[8,45],"significant":[9],"new":[10,46,156],"insights":[11,47],"into":[12,48],"the":[13,23,49,153,185],"evolution":[14,50],"of":[15,37,51,138,155,187],"a":[16,74,85,90,102,109,147],"morphologically":[17,52],"rich,":[18,53],"low-resource":[19,54],"language.":[20],"We":[21,77],"challenge":[22],"naive":[24],"assumption":[25],"that":[26,92,118],"linguistic":[27],"change":[28],"is":[29,93,127],"simplification":[30],"by":[31,146],"quantitatively":[32],"analyzing":[33],"over":[34],"2,000":[35],"years":[36],"Sanskrit,":[38],"demonstrating":[39],"weakly-supervised":[41],"languages.":[55],"Our":[56,115],"approach":[57],"addresses":[58],"data":[59],"scarcity":[60],"through":[61],"weak":[62],"supervision,":[63],"using":[64],"100+":[65],"high-precision":[66],"regex":[67],"patterns":[68,137],"to":[69,101,142],"generate":[70],"pseudo-labels":[71],"for":[72,190],"fine-tuning":[73],"multilingual":[75],"BERT.":[76],"then":[78],"fuse":[79],"symbolic":[80],"and":[81,96,152,176],"neural":[82],"outputs":[83],"via":[84],"novel":[86],"confidence-weighted":[87],"ensemble,":[88],"creating":[89],"system":[91,161],"both":[94],"scalable":[95],"interpretable.":[97],"Applying":[98],"this":[99],"framework":[100],"1.47-million-word":[103],"diachronic":[104],"corpus,":[105],"our":[106,160],"ensemble":[107],"achieves":[108],"52.4%":[110],"overall":[111,120,178],"feature":[112],"detection":[113],"rate.":[114],"findings":[116,189],"reveal":[117],"Sanskrit's":[119],"morphological":[121],"complexity":[122,140],"does":[123],"not":[124],"decrease":[125],"but":[126],"instead":[128],"dynamically":[129],"redistributed:":[130],"while":[131],"earlier":[132],"verbal":[133],"features":[134],"show":[135],"cyclical":[136],"decline,":[139],"shifts":[141],"other":[143],"domains,":[144],"evidenced":[145],"dramatic":[148],"expansion":[149],"in":[150],"compounding":[151],"emergence":[154],"philosophical":[157],"terminology.":[158],"Critically,":[159],"produces":[162],"well-calibrated":[163],"uncertainty":[164],"estimates,":[165],"with":[166,170],"confidence":[167],"strongly":[168],"correlating":[169],"accuracy":[171],"(Pearson":[172],"r":[173],"=":[174,182],"0.92)":[175],"low":[177],"calibration":[179],"error":[180],"(ECE":[181],"0.043),":[183],"bolstering":[184],"reliability":[186],"these":[188],"computational":[191],"philology.":[192]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-12-09T00:00:00"}