{"id":"https://openalex.org/W4385570063","doi":"https://doi.org/10.18653/v1/2023.acl-short.3","title":"Transformed Protoform Reconstruction","display_name":"Transformed Protoform Reconstruction","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4385570063","doi":"https://doi.org/10.18653/v1/2023.acl-short.3"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2023.acl-short.3","doi":"https://doi.org/10.18653/v1/2023.acl-short.3","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.acl-short.3","pdf_url":"https://aclanthology.org/2023.acl-short.3.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2023.acl-short.3.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Young Min Kim","orcid":null,"observed_orcids":[]},"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":"Young Min Kim","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027404450","display_name":"Kalvin Chang","orcid":null,"observed_orcids":[]},"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":["Language Technologies Institute, Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074099926","display_name":"Chenxuan Cui","orcid":null,"observed_orcids":[]},"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":"Chenxuan Cui","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, 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","observed_orcids":["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 R. Mortensen","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":17.9101,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.99278092,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"24","last_page":"38"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12768","display_name":"Linguistics and language evolution","score":0.8974999785423279,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12768","display_name":"Linguistics and language evolution","score":0.8974999785423279,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.0357000008225441,"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/T10028","display_name":"Topic Modeling","score":0.009100000374019146,"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/historical-phonology","display_name":"historical phonology","score":0.6869999766349792},{"id":"https://openalex.org/keywords/cognates","display_name":"cognates","score":0.5519999861717224},{"id":"https://openalex.org/keywords/latin","display_name":"Latin language","score":0.45100000500679016},{"id":"https://openalex.org/keywords/proto-romance","display_name":"Proto-Romance","score":0.7789999842643738},{"id":"https://openalex.org/keywords/vulgar-latin","display_name":"Vulgar Latin","score":0.9509999752044678},{"id":"https://openalex.org/keywords/romance-languages","display_name":"Romance languages","score":0.8820000290870667},{"id":"https://openalex.org/keywords/transformer","display_name":"transformer models","score":0.593999981880188},{"id":"https://openalex.org/keywords/phylogenetic-signal","display_name":"phylogenetic signal","score":0.7699999809265137},{"id":"https://openalex.org/keywords/morphological-reconstruction","display_name":"morphological reconstruction","score":0.43799999356269836}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7838618159294128},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6161595582962036},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6064174175262451},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5607948303222656},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.4959617555141449},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4942174255847931},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49154195189476013},{"id":"https://openalex.org/C165297611","wikidata":"https://www.wikidata.org/wiki/Q43249","display_name":"Morpheme","level":2,"score":0.46692582964897156},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4312478005886078},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4308752119541168},{"id":"https://openalex.org/C41132520","wikidata":"https://www.wikidata.org/wiki/Q19814","display_name":"Romance languages","level":2,"score":0.42557308077812195},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.41674378514289856},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.21899038553237915},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.20834249258041382},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.13224411010742188},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2023.acl-short.3","doi":"https://doi.org/10.18653/v1/2023.acl-short.3","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.acl-short.3","pdf_url":"https://aclanthology.org/2023.acl-short.3.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2307.01896","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2307.01896","pdf_url":"https://arxiv.org/pdf/2307.01896","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,"listed_in":[],"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":"doi:10.48550/arxiv.2307.01896","doi":"https://doi.org/10.48550/arxiv.2307.01896","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2307.01896","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,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2023.acl-short.3","doi":"https://doi.org/10.18653/v1/2023.acl-short.3","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.acl-short.3","pdf_url":"https://aclanthology.org/2023.acl-short.3.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385570063.pdf","grobid_xml":"https://content.openalex.org/works/W4385570063.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W1647671624","https://openalex.org/W2016381774","https://openalex.org/W2072240081","https://openalex.org/W2089679262","https://openalex.org/W2101234009","https://openalex.org/W2114055146","https://openalex.org/W2124613178","https://openalex.org/W2147880316","https://openalex.org/W2152076522","https://openalex.org/W2251845254","https://openalex.org/W2332672428","https://openalex.org/W2572670101","https://openalex.org/W2626778328","https://openalex.org/W2831901288","https://openalex.org/W2942741563","https://openalex.org/W2964199361","https://openalex.org/W2992559488","https://openalex.org/W3029986875","https://openalex.org/W3171575190","https://openalex.org/W3199943451","https://openalex.org/W4233201567","https://openalex.org/W4285240724","https://openalex.org/W4385572071","https://openalex.org/W4387627414","https://openalex.org/W4392267919","https://openalex.org/W4393416720","https://openalex.org/W6887807893"],"related_works":["https://openalex.org/W4395483264","https://openalex.org/W4417354626","https://openalex.org/W4385572071","https://openalex.org/W4389520718","https://openalex.org/W2831901288","https://openalex.org/W7097120722","https://openalex.org/W4389519390","https://openalex.org/W4412888218","https://openalex.org/W4287888416","https://openalex.org/W7165792028"],"abstract_inverted_index":{"Protoform":[0],"reconstruction":[1,30],"is":[2,97,121],"the":[3,25,42,94,109],"task":[4],"of":[5,15,18,54,66,78],"inferring":[6],"how":[7],"morphemes":[8],"or":[9,140],"words":[10],"sounded":[11],"in":[12,93],"ancestral":[13],"languages":[14,114],"a":[16,52,73,130],"set":[17],"daughter":[19],"languages.Meloni":[20],"et":[21,62],"al.":[22],"(2021)":[23],"achieved":[24],"stateof-the-art":[26],"on":[27,51,57],"Latin":[28,126],"protoform":[29],"with":[31,35,41],"an":[32],"RNN-based":[33],"encoder-decoder":[34],"attention":[36],"model.We":[37],"update":[38],"their":[39,49],"model":[40,47,50,87],"state-of-the-art":[43],"seq2seq":[44],"model-the":[45],"Transformer.Our":[46],"outperforms":[48],"suite":[53],"different":[55,59],"metrics":[56],"two":[58,147],"datasets:":[60],"Meloni":[61],"al.'s":[63],"Romance":[64,113],"data":[65],"8,000+":[67],"cognates":[68,80],"(spanning":[69,81],"5":[70],"languages)":[71],"and":[72,117,133],"Chinese":[74],"dataset":[75],"(H\u00f3u,":[76],"2004)":[77],"800+":[79],"39":[82],"varieties).We":[83],"also":[84],"probe":[85],"our":[86],"for":[88],"potential":[89],"phylogenetic":[90],"signal":[91],"contained":[92],"model.Our":[95],"code":[96],"publicly":[98],"available":[99],"1":[100,104],".*":[101],"Equal":[102],"contribution":[103],"https://github.com/cmu-llab/acl-2023":[105],"2":[106],"In":[107],"fact,":[108],"proto-language":[110],"from":[111],"which":[112],"like":[115],"Spanish":[116],"Italian":[118],"are":[119],"descended":[120],"not":[122],"identical":[123],"to":[124],"Classical":[125],"but":[127],"is,":[128],"rather,":[129],"closely":[131],"related":[132],"sparsely":[134],"attested":[135],"language":[136],"sometimes":[137],"called":[138],"Proto-Romance":[139],"Vulgar":[141],"Latin.'tooth'":[142],"'two'":[143],"'ten'":[144],"English":[145],"tooth":[146],"ten":[148],"t":[149,154],"Dutch":[150],"tand":[151],"twee":[152],"tien":[153],"German":[155]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":3}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2023-08-05T00:00:00"}
