{"id":"https://openalex.org/W3126545064","doi":"https://doi.org/10.15398/jlm.v8i2.268","title":"Word prediction in computational historical linguistics","display_name":"Word prediction in computational historical linguistics","publication_year":2021,"publication_date":"2021-02-04","ids":{"openalex":"https://openalex.org/W3126545064","doi":"https://doi.org/10.15398/jlm.v8i2.268","mag":"3126545064"},"language":"en","primary_location":{"id":"doi:10.15398/jlm.v8i2.268","doi":"https://doi.org/10.15398/jlm.v8i2.268","is_oa":true,"landing_page_url":"https://doi.org/10.15398/jlm.v8i2.268","pdf_url":"https://jlm.ipipan.waw.pl/index.php/JLM/article/download/268/248","source":{"id":"https://openalex.org/S4210167641","display_name":"Journal of Language Modelling","issn_l":"2299-8470","issn":["2299-8470","2299-856X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","ddh","doaj","erih-plus","jufo-1","norway-1","poland-40","russia-white-list-3","vabb-shw"],"host_organization":"https://openalex.org/P4310317485","host_organization_name":"Polish Academy of Sciences","host_organization_lineage":["https://openalex.org/P4310317485"],"host_organization_lineage_names":["Polish Academy of Sciences"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Language Modelling","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://jlm.ipipan.waw.pl/index.php/JLM/article/download/268/248","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083387162","display_name":"Peter Dekker","orcid":"https://orcid.org/0000-0003-4734-2668","observed_orcids":["https://orcid.org/0000-0003-4734-2668"]},"institutions":[{"id":"https://openalex.org/I13469542","display_name":"Vrije Universiteit Brussel","ror":"https://ror.org/006e5kg04","country_code":"BE","type":"education","lineage":["https://openalex.org/I13469542"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Peter Dekker","raw_affiliation_strings":["AI Lab, Vrije Universiteit Brussel"],"raw_orcid":"https://orcid.org/0000-0003-4734-2668","affiliations":[{"raw_affiliation_string":"AI Lab, Vrije Universiteit Brussel","institution_ids":["https://openalex.org/I13469542"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007928903","display_name":"Willem H. Zuidema","orcid":"https://orcid.org/0000-0002-2362-5447","observed_orcids":["https://orcid.org/0000-0002-2362-5447"]},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Willem Zuidema","raw_affiliation_strings":["Institute for Logic, Language and Computation, University of Amsterdam"],"raw_orcid":"https://orcid.org/0000-0002-2362-5447","affiliations":[{"raw_affiliation_string":"Institute for Logic, Language and Computation, University of Amsterdam","institution_ids":["https://openalex.org/I887064364"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.2851,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.96100523,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":98},"biblio":{"volume":"8","issue":"2","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12768","display_name":"Linguistics and language evolution","score":0.6875,"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":0.6875,"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":0.2190999984741211,"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/T12377","display_name":"Digital Humanities and Scholarship","score":0.02539999969303608,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/word-prediction","display_name":"word prediction","score":0.9929999709129333},{"id":"https://openalex.org/keywords/computational-historical-linguistics","display_name":"computational historical linguistics","score":0.9660000205039978},{"id":"https://openalex.org/keywords/sound-correspondences","display_name":"sound correspondences","score":0.48899999260902405},{"id":"https://openalex.org/keywords/cognate-detection","display_name":"cognate detection","score":0.9520000219345093},{"id":"https://openalex.org/keywords/phylogenetic-reconstruction","display_name":"phylogenetic inference","score":0.9940000176429749},{"id":"https://openalex.org/keywords/linguistic-reconstruction","display_name":"language reconstruction","score":0.8029999732971191},{"id":"https://openalex.org/keywords/data-representation","display_name":"data representation","score":0.6480000019073486},{"id":"https://openalex.org/keywords/machine-learning-models","display_name":"machine learning models","score":0.8769999742507935}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7714837789535522},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6325371265411377},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6274279356002808},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.6232951283454895},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5865098834037781},{"id":"https://openalex.org/C2777392089","wikidata":"https://www.wikidata.org/wiki/Q690548","display_name":"Cognate","level":2,"score":0.5654946565628052},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.562882661819458},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5472788214683533},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5364433526992798},{"id":"https://openalex.org/C524601802","wikidata":"https://www.wikidata.org/wiki/Q2198157","display_name":"Quantitative linguistics","level":3,"score":0.4892008304595947},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4698955714702606},{"id":"https://openalex.org/C181925144","wikidata":"https://www.wikidata.org/wiki/Q190375","display_name":"Historical linguistics","level":2,"score":0.41316473484039307},{"id":"https://openalex.org/C167055898","wikidata":"https://www.wikidata.org/wiki/Q321249","display_name":"Applied linguistics","level":2,"score":0.3540192246437073},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.15398/jlm.v8i2.268","doi":"https://doi.org/10.15398/jlm.v8i2.268","is_oa":true,"landing_page_url":"https://doi.org/10.15398/jlm.v8i2.268","pdf_url":"https://jlm.ipipan.waw.pl/index.php/JLM/article/download/268/248","source":{"id":"https://openalex.org/S4210167641","display_name":"Journal of Language Modelling","issn_l":"2299-8470","issn":["2299-8470","2299-856X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","ddh","doaj","erih-plus","jufo-1","norway-1","poland-40","russia-white-list-3","vabb-shw"],"host_organization":"https://openalex.org/P4310317485","host_organization_name":"Polish Academy of Sciences","host_organization_lineage":["https://openalex.org/P4310317485"],"host_organization_lineage_names":["Polish Academy of Sciences"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Language Modelling","raw_type":"journal-article"},{"id":"pmh:oai:dare.uva.nl:openaire/03b024a7-2599-46b6-a3f0-d99a572a62b0","doi":null,"is_oa":true,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/word-prediction-in-computational-historical-linguistics(03b024a7-2599-46b6-a3f0-d99a572a62b0).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"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":"Dekker, P & Zuidema, W 2020, 'Word prediction in computational historical linguistics', Journal of Language Modelling, vol. 8, no. 2, pp. 295-336. https://doi.org/10.15398/JLM.V8I2.268","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:doaj.org/article:f440f75a1b24467693697375af300880","doi":null,"is_oa":true,"landing_page_url":"https://doaj.org/article/f440f75a1b24467693697375af300880","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Language Modelling, Vol 8, Iss 2, Pp 295\u2013336-295\u2013336 (2021)","raw_type":"article"},{"id":"pmh:oai:vubissmart:VUBISSMART:2000:147587","doi":null,"is_oa":false,"landing_page_url":"https://biblio.vub.ac.be/vubir/word-prediction-in-computational-historical-linguistics(ac82f156-a611-4697-93ac-da58dcf276ff).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306402573","display_name":"VUBIR (Vrije Universiteit Brussel)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I13469542","host_organization_name":"Vrije Universiteit Brussel","host_organization_lineage":["https://openalex.org/I13469542"],"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":"article"}],"best_oa_location":{"id":"doi:10.15398/jlm.v8i2.268","doi":"https://doi.org/10.15398/jlm.v8i2.268","is_oa":true,"landing_page_url":"https://doi.org/10.15398/jlm.v8i2.268","pdf_url":"https://jlm.ipipan.waw.pl/index.php/JLM/article/download/268/248","source":{"id":"https://openalex.org/S4210167641","display_name":"Journal of Language Modelling","issn_l":"2299-8470","issn":["2299-8470","2299-856X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","ddh","doaj","erih-plus","jufo-1","norway-1","poland-40","russia-white-list-3","vabb-shw"],"host_organization":"https://openalex.org/P4310317485","host_organization_name":"Polish Academy of Sciences","host_organization_lineage":["https://openalex.org/P4310317485"],"host_organization_lineage_names":["Polish Academy of Sciences"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Language Modelling","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G2084304408","display_name":null,"funder_award_id":"024.001.006","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"},{"id":"https://openalex.org/G4627615187","display_name":null,"funder_award_id":"Gravitation Grant (024.001.006)","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"},{"id":"https://openalex.org/G7361519743","display_name":"Identifying drivers of language change using neural agent-based models","funder_award_id":"11A2821N","funder_id":"https://openalex.org/F4320321730","funder_display_name":"Fonds Wetenschappelijk Onderzoek"}],"funders":[{"id":"https://openalex.org/F4320321730","display_name":"Fonds Wetenschappelijk Onderzoek","ror":"https://ror.org/03qtxy027"},{"id":"https://openalex.org/F4320321800","display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","ror":"https://ror.org/04jsz6e67"},{"id":"https://openalex.org/F4320327336","display_name":"Vlaamse regering","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3126545064.pdf","grobid_xml":"https://content.openalex.org/works/W3126545064.grobid-xml"},"referenced_works_count":80,"referenced_works":["https://openalex.org/W1165382972","https://openalex.org/W1533861849","https://openalex.org/W1585280831","https://openalex.org/W1593045043","https://openalex.org/W1597078689","https://openalex.org/W1647671624","https://openalex.org/W1963230138","https://openalex.org/W1978384785","https://openalex.org/W1979618484","https://openalex.org/W1991133427","https://openalex.org/W2016156565","https://openalex.org/W2019689476","https://openalex.org/W2040870580","https://openalex.org/W2044352052","https://openalex.org/W2054658115","https://openalex.org/W2072240081","https://openalex.org/W2089679262","https://openalex.org/W2097706568","https://openalex.org/W2098524338","https://openalex.org/W2110620844","https://openalex.org/W2112648537","https://openalex.org/W2121564430","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2137614260","https://openalex.org/W2145715272","https://openalex.org/W2146502635","https://openalex.org/W2147880316","https://openalex.org/W2152076522","https://openalex.org/W2153579005","https://openalex.org/W2157331557","https://openalex.org/W2170199215","https://openalex.org/W2229908198","https://openalex.org/W2242818861","https://openalex.org/W2250539671","https://openalex.org/W2251111702","https://openalex.org/W2251122464","https://openalex.org/W2251659274","https://openalex.org/W2251845254","https://openalex.org/W2251846372","https://openalex.org/W2277953252","https://openalex.org/W2313511355","https://openalex.org/W2319920447","https://openalex.org/W2509231472","https://openalex.org/W2572149853","https://openalex.org/W2621675718","https://openalex.org/W2626778328","https://openalex.org/W2762143087","https://openalex.org/W2773750487","https://openalex.org/W2782401228","https://openalex.org/W2788886867","https://openalex.org/W2803395244","https://openalex.org/W2812783770","https://openalex.org/W2831901288","https://openalex.org/W2895423358","https://openalex.org/W2896941665","https://openalex.org/W2950825792","https://openalex.org/W2951559648","https://openalex.org/W2951697870","https://openalex.org/W2956028016","https://openalex.org/W2956086512","https://openalex.org/W2963341956","https://openalex.org/W2965572880","https://openalex.org/W2979390785","https://openalex.org/W2979401726","https://openalex.org/W2982690190","https://openalex.org/W2992559488","https://openalex.org/W2993818995","https://openalex.org/W3029488254","https://openalex.org/W3029986875","https://openalex.org/W3030075662","https://openalex.org/W3048942065","https://openalex.org/W3137111878","https://openalex.org/W4212864386","https://openalex.org/W4230213531","https://openalex.org/W4230872509","https://openalex.org/W4251828327","https://openalex.org/W4254240410","https://openalex.org/W4256264394","https://openalex.org/W6969173555"],"related_works":["https://openalex.org/W4389520718","https://openalex.org/W2956028016","https://openalex.org/W2888877568","https://openalex.org/W6941338158","https://openalex.org/W7151214098","https://openalex.org/W2965572880","https://openalex.org/W2149823587","https://openalex.org/W4385572071","https://openalex.org/W3114956663","https://openalex.org/W4292735420"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"investigate":[4],"how":[5],"the":[6,35,47,50,93],"prediction":[7,29,58,108],"paradigm":[8],"from":[9,46],"machine":[10,96],"learning":[11,97],"and":[12,71,92,118],"Natural":[13],"Language":[14],"Processing":[15],"(NLP)":[16],"can":[17],"be":[18,102],"put":[19],"to":[20,61,77,101],"use":[21],"in":[22,40,53,74,110,124],"computational":[23],"historical":[24,111,125],"linguistics.":[25,112,126],"We":[26,83,113],"propose":[27],"word":[28],"as":[30,89],"an":[31],"intermediate":[32],"task,":[33],"where":[34],"forms":[36,48],"of":[37,49,95],"unseen":[38],"words":[39,52],"some":[41],"target":[42],"language":[43],"are":[44],"predicted":[45],"corresponding":[51],"a":[54],"source":[55],"language.":[56],"Word":[57],"allows":[59],"us":[60],"develop":[62],"algorithms":[63],"for":[64,80],"phylogenetic":[65],"tree":[66],"reconstruction,":[67],"sound":[68],"correspondence":[69],"identification":[70],"cognate":[72],"detection,":[73],"ways":[75],"close":[76],"attested":[78],"methods":[79,109],"linguistic":[81],"reconstruction.":[82],"will":[84],"discuss":[85],"different":[86,122],"factors,":[87],"such":[88],"data":[90],"representation":[91],"choice":[94],"model,":[98],"that":[99],"have":[100],"taken":[103],"into":[104],"account":[105],"when":[106],"applying":[107],"present":[114],"our":[115],"own":[116],"implementations":[117],"evaluate":[119],"them":[120],"on":[121],"tasks":[123]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":7}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2021-02-15T00:00:00"}
