{"id":"https://openalex.org/W4402671328","doi":"https://doi.org/10.18653/v1/2024.acl-long.788","title":"Semisupervised Neural Proto-Language Reconstruction","display_name":"Semisupervised Neural Proto-Language Reconstruction","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4402671328","doi":"https://doi.org/10.18653/v1/2024.acl-long.788"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2024.acl-long.788","doi":"https://doi.org/10.18653/v1/2024.acl-long.788","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.acl-long.788","pdf_url":"https://aclanthology.org/2024.acl-long.788.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 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2024.acl-long.788.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101607148","display_name":"Liang Lu","orcid":"https://orcid.org/0000-0003-4005-679X","observed_orcids":["https://orcid.org/0000-0003-4005-679X"]},"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":"Liang Lu","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111226567","display_name":"Peirong Xie","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peirong Xie","raw_affiliation_strings":["University of Southern California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California","institution_ids":["https://openalex.org/I1174212"]}]},{"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 Mortensen","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"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":13.849,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.98471585,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"14715","last_page":"14759"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12768","display_name":"Linguistics and language evolution","score":0.6776999831199646,"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":0.6776999831199646,"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":0.14749999344348907,"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":0.062300000339746475,"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-linguistics","display_name":"historical linguistics","score":0.7149999737739563},{"id":"https://openalex.org/keywords/comparative-reconstruction","display_name":"comparative reconstruction","score":0.777999997138977},{"id":"https://openalex.org/keywords/semi-supervised-learning","display_name":"semi-supervised learning","score":0.9359999895095825},{"id":"https://openalex.org/keywords/cognate-sets","display_name":"cognate sets","score":0.9300000071525574},{"id":"https://openalex.org/keywords/ancestral-languages","display_name":"ancestral languages","score":0.5580000281333923},{"id":"https://openalex.org/keywords/unlabeled-data","display_name":"unlabeled data","score":0.6399999856948853},{"id":"https://openalex.org/keywords/comparative-analysis","display_name":"comparative analysis","score":0.5479999780654907}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7242934107780457},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5557981133460999},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5464545488357544}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2024.acl-long.788","doi":"https://doi.org/10.18653/v1/2024.acl-long.788","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.acl-long.788","pdf_url":"https://aclanthology.org/2024.acl-long.788.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 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2406.05930","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.05930","pdf_url":"https://arxiv.org/pdf/2406.05930","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.2406.05930","doi":"https://doi.org/10.48550/arxiv.2406.05930","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2406.05930","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/v1/2024.acl-long.788","doi":"https://doi.org/10.18653/v1/2024.acl-long.788","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.acl-long.788","pdf_url":"https://aclanthology.org/2024.acl-long.788.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 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320310207","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402671328.pdf","grobid_xml":"https://content.openalex.org/works/W4402671328.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2965572880","https://openalex.org/W4385572071","https://openalex.org/W3137111878","https://openalex.org/W7131787635","https://openalex.org/W4417354626","https://openalex.org/W3172179742","https://openalex.org/W2030379352","https://openalex.org/W569241374","https://openalex.org/W4395483264","https://openalex.org/W2831901288"],"abstract_inverted_index":{"Existing":[0],"work":[1],"implementing":[2],"comparative":[3,74,83],"reconstruction":[4,15,38,75],"of":[5,19,31,51,62,132],"ancestral":[6],"languages":[7],"(protolanguages)":[8],"has":[9],"usually":[10],"required":[11],"full":[12],"supervision.However,":[13],"historical":[14,37],"models":[16],"are":[17],"only":[18,47,90],"practical":[20],"value":[21],"if":[22],"they":[23],"can":[24],"be":[25,91],"trained":[26,45],"with":[27,56],"a":[28,35,48,59,70],"limited":[29],"amount":[30,50,61],"labeled":[32,52],"data.We":[33],"propose":[34,69],"semisupervised":[36,120],"task":[39,125],"in":[40],"which":[41],"the":[42],"model":[43],"is":[44,110],"on":[46,122],"small":[49],"data":[53,64],"(cognate":[54,65],"sets":[55,66,116],"proto-forms)":[57],"and":[58,136],"large":[60],"unlabeled":[63,114],"without":[67],"proto-forms).We":[68],"neural":[71],"architecture":[72,109],"for":[73],"(DPD-BiReconstructor)":[76],"incorporating":[77],"an":[78],"essential":[79],"insight":[80],"from":[81,93],"linguists'":[82],"method:":[84],"that":[85,107],"reconstructed":[86],"words":[87],"should":[88],"not":[89],"reconstructable":[92],"their":[94,103],"daughter":[95,104],"words,":[96],"but":[97],"also":[98],"deterministically":[99],"transformable":[100],"back":[101],"into":[102],"words.We":[105],"show":[106],"this":[108,123],"able":[111],"to":[112,117],"leverage":[113],"cognate":[115],"outperform":[118],"strong":[119],"baselines":[121],"novel":[124],"1":[126],".Vladimir":[127],"I.":[128],"Levenshtein.1966.Binary":[129],"codes":[130],"capable":[131],"correcting":[133],"deletions,":[134],"insertions,":[135],"reversals.In":[137],"Soviet":[138],"Physics":[139],"Doklady,":[140],"volume":[141],"10,":[142],"pages":[143],"707-710.Soviet":[144],"Union.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2024-09-21T00:00:00"}
