{"id":"https://openalex.org/W4389524584","doi":"https://doi.org/10.18653/v1/2023.lchange-1.14","title":"Automating Sound Change Prediction for Phylogenetic Inference: A Tukanoan Case Study","display_name":"Automating Sound Change Prediction for Phylogenetic Inference: A Tukanoan Case Study","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4389524584","doi":"https://doi.org/10.18653/v1/2023.lchange-1.14"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2023.lchange-1.14","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2023.lchange-1.14","pdf_url":"https://aclanthology.org/2023.lchange-1.14.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 4th Workshop on Computational Approaches to Historical Language Change","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2023.lchange-1.14.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027404450","display_name":"Kalvin Chang","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kalvin Chang","raw_affiliation_strings":["School of Computer Science, Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074198234","display_name":"Nathaniel D. Robinson","orcid":"https://orcid.org/0000-0002-2773-5096"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nathaniel Robinson","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University","School of Computer Science, Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"School of Computer Science, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026746531","display_name":"Anna Cai","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anna Cai","raw_affiliation_strings":["School of Computer Science, Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100443161","display_name":"Ting Chen","orcid":"https://orcid.org/0000-0001-5468-1348"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ting Chen","raw_affiliation_strings":["School of Computer Science, Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004082452","display_name":"Annie Zhang","orcid":"https://orcid.org/0009-0002-3104-8587"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Annie Zhang","raw_affiliation_strings":["School of Computer Science, Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059859009","display_name":"David R. Mortensen","orcid":"https://orcid.org/0000-0002-3927-6851"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Mortensen","raw_affiliation_strings":["School of Computer Science, Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.28506271,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"129","last_page":"142"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12090","display_name":"Language and cultural evolution","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9902999997138977,"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/T11640","display_name":"Linguistic Variation and Morphology","score":0.972100019454956,"subfield":{"id":"https://openalex.org/subfields/3310","display_name":"Linguistics and Language"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7384289503097534},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6813105344772339},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.6025821566581726},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5793320536613464},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5422840714454651},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5353792905807495},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.48514971137046814},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.4825577139854431},{"id":"https://openalex.org/keywords/sound-change","display_name":"Sound change","score":0.4706494212150574},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.46700677275657654},{"id":"https://openalex.org/keywords/phylogenetic-tree","display_name":"Phylogenetic tree","score":0.4483897089958191},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.44328972697257996},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42441433668136597},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.352236807346344},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17805063724517822},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.14796322584152222},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12126529216766357}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7384289503097534},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6813105344772339},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.6025821566581726},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5793320536613464},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5422840714454651},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5353792905807495},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.48514971137046814},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.4825577139854431},{"id":"https://openalex.org/C2779879116","wikidata":"https://www.wikidata.org/wiki/Q754984","display_name":"Sound change","level":2,"score":0.4706494212150574},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.46700677275657654},{"id":"https://openalex.org/C193252679","wikidata":"https://www.wikidata.org/wiki/Q242125","display_name":"Phylogenetic tree","level":3,"score":0.4483897089958191},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.44328972697257996},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42441433668136597},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.352236807346344},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17805063724517822},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.14796322584152222},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12126529216766357},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2023.lchange-1.14","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2023.lchange-1.14","pdf_url":"https://aclanthology.org/2023.lchange-1.14.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 4th Workshop on Computational Approaches to Historical Language Change","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2023.lchange-1.14","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2023.lchange-1.14","pdf_url":"https://aclanthology.org/2023.lchange-1.14.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 4th Workshop on Computational Approaches to Historical Language Change","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6299999952316284,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4389524584.pdf"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W85754767","https://openalex.org/W2021031353","https://openalex.org/W2044352052","https://openalex.org/W2065973977","https://openalex.org/W2069285862","https://openalex.org/W2073610029","https://openalex.org/W2074231493","https://openalex.org/W2152076522","https://openalex.org/W2223947020","https://openalex.org/W2312382848","https://openalex.org/W2313511355","https://openalex.org/W2316622809","https://openalex.org/W2572670101","https://openalex.org/W2788765591","https://openalex.org/W2799904685","https://openalex.org/W2895423358","https://openalex.org/W2963143413","https://openalex.org/W2972634180","https://openalex.org/W3001922427","https://openalex.org/W3092158442","https://openalex.org/W3199943451","https://openalex.org/W4205285807","https://openalex.org/W4205712896","https://openalex.org/W4205789022","https://openalex.org/W4211171424","https://openalex.org/W4283711459","https://openalex.org/W4298327575"],"related_works":["https://openalex.org/W2361861616","https://openalex.org/W2263699433","https://openalex.org/W2377979023","https://openalex.org/W2218034408","https://openalex.org/W2392921965","https://openalex.org/W2358755282","https://openalex.org/W2391573755","https://openalex.org/W2625833328","https://openalex.org/W2365451235","https://openalex.org/W2360415018"],"abstract_inverted_index":{"We":[0,113,127],"describe":[1],"a":[2,25,35,42,70,76,93,100,106,131],"set":[3],"of":[4,38,75,97],"new":[5],"methods":[6],"to":[7,29,50,119],"partially":[8],"automate":[9],"linguistic":[10,71],"phylogenetic":[11,78],"inference":[12,79],"given":[13],"(1)":[14],"cognate":[15],"sets":[16],"with":[17,92,130],"their":[18,30,66],"respective":[19],"protoforms":[20,64],"and":[21,33,56,65,117,123],"sound":[22,39,47,59,137,145],"laws,":[23],"(2)":[24],"mapping":[26],"from":[27,99,147],"phones":[28,55],"articulatory":[31,52],"features":[32],"(3)":[34],"typological":[36],"database":[37],"changes.We":[40],"train":[41],"neural":[43,121],"network":[44],"on":[45,85],"these":[46],"change":[48,60],"data":[49],"weight":[51],"distances":[53],"between":[54,62],"predict":[57],"intermediate":[58],"steps":[61],"historical":[63],"modern":[67],"descendants,":[68],"replacing":[69],"expert":[72,104,148],"in":[73],"part":[74],"parsimony-based":[77,124],"algorithm.":[80],"In":[81],"our":[82,120],"best":[83],"experiments":[84],"Tukanoan":[86],"languages,":[87],"this":[88],"method":[89],"produces":[90],"trees":[91],"Generalized":[94],"Quartet":[95],"Distance":[96],"0.12":[98],"tree":[101,125],"that":[102],"used":[103],"annotations,":[105],"significant":[107],"improvement":[108],"over":[109],"other":[110],"semi-automated":[111],"baselines.":[112],"discuss":[114],"potential":[115],"benefits":[116],"drawbacks":[118],"approach":[122],"prediction.":[126],"also":[128],"experiment":[129],"minimal":[132],"generalization":[133],"learner":[134],"for":[135],"automatic":[136],"law":[138],"induction,":[139],"finding":[140],"it":[141],"less":[142],"effective":[143],"than":[144],"laws":[146],"annotation.":[149],"Our":[150],"code":[151],"is":[152],"publicly":[153],"available.":[154]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}