{"id":"https://openalex.org/W2979390785","doi":"https://doi.org/10.1162/coli_a_00361","title":"Automatic Identification and Production of Related Words for Historical Linguistics","display_name":"Automatic Identification and Production of Related Words for Historical Linguistics","publication_year":2019,"publication_date":"2019-10-08","ids":{"openalex":"https://openalex.org/W2979390785","doi":"https://doi.org/10.1162/coli_a_00361","mag":"2979390785"},"language":"en","primary_location":{"id":"doi:10.1162/coli_a_00361","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00361","pdf_url":"https://www.mitpressjournals.org/doi/pdf/10.1162/coli_a_00361","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.mitpressjournals.org/doi/pdf/10.1162/coli_a_00361","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038156267","display_name":"Alina Maria Ciobanu","orcid":null},"institutions":[{"id":"https://openalex.org/I141595442","display_name":"University of Bucharest","ror":"https://ror.org/02x2v6p15","country_code":"RO","type":"education","lineage":["https://openalex.org/I141595442"]}],"countries":["RO"],"is_corresponding":true,"raw_author_name":"Alina Maria Ciobanu","raw_affiliation_strings":["University of Bucharest, Department of Computer Science, HLT Research Center"],"affiliations":[{"raw_affiliation_string":"University of Bucharest, Department of Computer Science, HLT Research Center","institution_ids":["https://openalex.org/I141595442"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057738797","display_name":"Liviu P. Dinu","orcid":"https://orcid.org/0000-0002-7559-6756"},"institutions":[{"id":"https://openalex.org/I141595442","display_name":"University of Bucharest","ror":"https://ror.org/02x2v6p15","country_code":"RO","type":"education","lineage":["https://openalex.org/I141595442"]}],"countries":["RO"],"is_corresponding":true,"raw_author_name":"Liviu P. Dinu","raw_affiliation_strings":["University of Bucharest, Department of Computer Science, HLT Research Center"],"affiliations":[{"raw_affiliation_string":"University of Bucharest, Department of Computer Science, HLT Research Center","institution_ids":["https://openalex.org/I141595442"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5038156267","https://openalex.org/A5057738797"],"corresponding_institution_ids":["https://openalex.org/I141595442"],"apc_list":null,"apc_paid":null,"fwci":1.4002,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.86537923,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"45","issue":"4","first_page":"667","last_page":"704"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9995999932289124,"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/T12090","display_name":"Language and cultural evolution","score":0.9980000257492065,"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/T11640","display_name":"Linguistic Variation and Morphology","score":0.9914000034332275,"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/computer-science","display_name":"Computer science","score":0.8371509313583374},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7041922807693481},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6626229286193848},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6377211213111877},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5596398115158081},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5386903285980225},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5268111228942871},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.453308641910553},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4357861578464508},{"id":"https://openalex.org/keywords/orthographic-projection","display_name":"Orthographic projection","score":0.4142061173915863},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.41316381096839905}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8371509313583374},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7041922807693481},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6626229286193848},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6377211213111877},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5596398115158081},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5386903285980225},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5268111228942871},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.453308641910553},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4357861578464508},{"id":"https://openalex.org/C175694140","wikidata":"https://www.wikidata.org/wiki/Q980329","display_name":"Orthographic projection","level":2,"score":0.4142061173915863},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.41316381096839905},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1162/coli_a_00361","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00361","pdf_url":"https://www.mitpressjournals.org/doi/pdf/10.1162/coli_a_00361","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:0e81237d25a045f298da1f8f7d71a810","is_oa":true,"landing_page_url":"https://doaj.org/article/0e81237d25a045f298da1f8f7d71a810","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computational Linguistics, Vol 45, Iss 4, Pp 667-704 (2020)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/coli_a_00361","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00361","pdf_url":"https://www.mitpressjournals.org/doi/pdf/10.1162/coli_a_00361","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6299999952316284,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2979390785.pdf","grobid_xml":"https://content.openalex.org/works/W2979390785.grobid-xml"},"referenced_works_count":88,"referenced_works":["https://openalex.org/W112217986","https://openalex.org/W122244083","https://openalex.org/W222053410","https://openalex.org/W584632868","https://openalex.org/W650128453","https://openalex.org/W1493923506","https://openalex.org/W1508337977","https://openalex.org/W1510073064","https://openalex.org/W1524281572","https://openalex.org/W1543107604","https://openalex.org/W1552011858","https://openalex.org/W1636585317","https://openalex.org/W1647671624","https://openalex.org/W1749856071","https://openalex.org/W1902237438","https://openalex.org/W1970013034","https://openalex.org/W1973976514","https://openalex.org/W1977468919","https://openalex.org/W1979618484","https://openalex.org/W1980219648","https://openalex.org/W1982365650","https://openalex.org/W1987718503","https://openalex.org/W1989327099","https://openalex.org/W1991995555","https://openalex.org/W2024561884","https://openalex.org/W2030379352","https://openalex.org/W2038721957","https://openalex.org/W2039451809","https://openalex.org/W2052954051","https://openalex.org/W2068448872","https://openalex.org/W2071014197","https://openalex.org/W2074231493","https://openalex.org/W2075149030","https://openalex.org/W2083808824","https://openalex.org/W2087064593","https://openalex.org/W2089679262","https://openalex.org/W2104924517","https://openalex.org/W2112279101","https://openalex.org/W2115755647","https://openalex.org/W2121764321","https://openalex.org/W2125257703","https://openalex.org/W2125670750","https://openalex.org/W2127783607","https://openalex.org/W2133990480","https://openalex.org/W2138247936","https://openalex.org/W2138500330","https://openalex.org/W2142046204","https://openalex.org/W2146563945","https://openalex.org/W2147880316","https://openalex.org/W2148038915","https://openalex.org/W2149823587","https://openalex.org/W2153599831","https://openalex.org/W2153635508","https://openalex.org/W2157268555","https://openalex.org/W2162017663","https://openalex.org/W2169232192","https://openalex.org/W2170199215","https://openalex.org/W2176198960","https://openalex.org/W2251111702","https://openalex.org/W2251201284","https://openalex.org/W2251659274","https://openalex.org/W2251845254","https://openalex.org/W2252037170","https://openalex.org/W2252176059","https://openalex.org/W2294829650","https://openalex.org/W2408423129","https://openalex.org/W2483327705","https://openalex.org/W2504681067","https://openalex.org/W2560220909","https://openalex.org/W2572149853","https://openalex.org/W2581563496","https://openalex.org/W2619421943","https://openalex.org/W2756976246","https://openalex.org/W2759990433","https://openalex.org/W2771976988","https://openalex.org/W2803395244","https://openalex.org/W2831901288","https://openalex.org/W2887428522","https://openalex.org/W2896693896","https://openalex.org/W2914244059","https://openalex.org/W2930957955","https://openalex.org/W2963010813","https://openalex.org/W4214671568","https://openalex.org/W4214718481","https://openalex.org/W4232937906","https://openalex.org/W4234065476","https://openalex.org/W4235505822","https://openalex.org/W4236615369"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2761785940","https://openalex.org/W2110523656","https://openalex.org/W1482209366","https://openalex.org/W2521627374"],"abstract_inverted_index":{"Language":[0],"change":[1],"across":[2],"space":[3],"and":[4,24,105,110,132,144,160,213],"time":[5],"is":[6,178,306],"one":[7],"of":[8,30,65,125,141,149,182,218,222,247,300],"the":[9,28,115,123,139,163,171,179,224,245,256,263,298],"main":[10],"concerns":[11],"in":[12,27,90,170,226,239,308],"historical":[13,309],"linguistics.":[14],"In":[15],"this":[16,177,183],"article,":[17],"we":[18,34,68,113,161,186,203,243],"develop":[19,70,187],"tools":[20],"to":[21,38,92,106,117,121,284],"assist":[22],"researchers":[23],"domain":[25],"experts":[26],"study":[29],"language":[31,143,150,229],"evolution.":[32],"First,":[33],"introduce":[35],"a":[36,62,118,135,142,146,188],"method":[37,116,191,283],"automatically":[39,193],"determine":[40],"whether":[41],"two":[42,206],"words":[43,100,225,261],"are":[44,313],"cognates.":[45,80,215],"We":[46,81,152,197,266,280],"propose":[47],"an":[48,227,274],"algorithm":[49],"for":[50,78,87,95,192,277],"extracting":[51],"cognates":[52,109,131],"from":[53,230,269],"electronic":[54],"dictionaries":[55],"that":[56,154,167,258,289],"contain":[57],"etymological":[58],"information.":[59],"Having":[60,235],"built":[61],"data":[63,286],"set":[64],"related":[66,195,207],"words,":[67],"further":[69],"machine":[71,189],"learning":[72,190],"methods":[73],"based":[74],"on":[75,199,255,293],"orthographic":[76,155],"alignment":[77],"identifying":[79],"use":[82],"aligned":[83],"subsequences":[84],"as":[85],"features":[86,156],"classification":[88,172],"algorithms":[89],"order":[91],"infer":[93,244],"rules":[94],"linguistic":[96,165],"changes":[97],"undergone":[98],"by":[99],"when":[101,260],"entering":[102],"new":[103],"languages":[104],"discriminate":[107],"between":[108,127,130],"non-cognates.":[111],"Second,":[112],"extend":[114],"finer-grained":[119],"level,":[120],"identify":[122],"type":[124],"relationship":[126],"words.":[128,196],"Discriminating":[129],"borrowings":[133],"provides":[134],"deeper":[136],"insight":[137],"into":[138],"history":[140],"allows":[145],"better":[147],"characterization":[148],"relatedness.":[151],"show":[153],"have":[157],"discriminative":[158],"power":[159],"analyze":[162],"underlying":[164],"factors":[166],"prove":[168],"relevant":[169],"task.":[173],"To":[174],"our":[175,282,290],"knowledge,":[176],"first":[180],"attempt":[181],"kind.":[184],"Third,":[185],"producing":[194,209,214],"focus":[198],"reconstructing":[200,219,278],"proto-words,":[201],"but":[202],"also":[204,296],"address":[205],"sub-problems,":[208],"modern":[210,232,236,264,271],"word":[211,237],"forms":[212,238],"The":[216],"task":[217],"proto-words":[220],"consists":[221],"recreating":[223],"ancient":[228],"its":[231],"daughter":[233],"languages.":[234,265],"multiple":[240,285],"Romance":[241],"languages,":[242,272],"form":[246],"their":[248],"common":[249],"Latin":[250],"ancestors.":[251],"Our":[252],"approach":[253,291],"relies":[254],"regularities":[257],"occurred":[259],"entered":[262],"leverage":[267],"information":[268],"several":[270],"building":[273],"ensemble":[275],"system":[276],"proto-words.":[279],"apply":[281],"sets,":[287],"showing":[288],"improves":[292],"previous":[294],"results,":[295],"having":[297],"advantage":[299],"requiring":[301],"less":[302],"input":[303],"data,":[304],"which":[305],"essential":[307],"linguistics,":[310],"where":[311],"resources":[312],"generally":[314],"scarce.":[315]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}