{"id":"https://openalex.org/W4405290311","doi":"https://doi.org/10.15398/jlm.v12i2.351","title":"Corpus-based measures discriminate inflection and derivation cross-linguistically","display_name":"Corpus-based measures discriminate inflection and derivation cross-linguistically","publication_year":2024,"publication_date":"2024-12-10","ids":{"openalex":"https://openalex.org/W4405290311","doi":"https://doi.org/10.15398/jlm.v12i2.351"},"language":"en","primary_location":{"id":"doi:10.15398/jlm.v12i2.351","is_oa":true,"landing_page_url":"https://doi.org/10.15398/jlm.v12i2.351","pdf_url":"https://213.135.36.146/index.php/JLM/article/download/351/292","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,"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"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://213.135.36.146/index.php/JLM/article/download/351/292","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053321639","display_name":"Coleman Haley","orcid":"https://orcid.org/0000-0003-3089-9558"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Coleman Haley","raw_affiliation_strings":["University of Edinburgh"],"raw_orcid":"https://orcid.org/0000-0003-3089-9558","affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014613113","display_name":"Edoardo Maria Ponti","orcid":"https://orcid.org/0000-0002-6308-1050"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Edoardo M. Ponti","raw_affiliation_strings":["University of Edinburgh"],"raw_orcid":"https://orcid.org/0000-0002-6308-1050","affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075564798","display_name":"Sharon Goldwater","orcid":"https://orcid.org/0000-0002-7298-0947"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sharon Goldwater","raw_affiliation_strings":["University of Edinburgh"],"raw_orcid":"https://orcid.org/0000-0002-7298-0947","affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15735201,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"12","issue":"2","first_page":"477","last_page":"529"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9922999739646912,"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/T10034","display_name":"Syntax, Semantics, Linguistic Variation","score":0.991599977016449,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/inflection","display_name":"Inflection","score":0.864642858505249},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.6714854836463928},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.5527235865592957},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4995381832122803},{"id":"https://openalex.org/keywords/boundary","display_name":"Boundary (topology)","score":0.47558343410491943},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.46172064542770386},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.44141316413879395},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39069172739982605},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34634438157081604},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.19871783256530762}],"concepts":[{"id":"https://openalex.org/C159403335","wikidata":"https://www.wikidata.org/wiki/Q207857","display_name":"Inflection","level":2,"score":0.864642858505249},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.6714854836463928},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5527235865592957},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4995381832122803},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.47558343410491943},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.46172064542770386},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.44141316413879395},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39069172739982605},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34634438157081604},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.19871783256530762},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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":4,"locations":[{"id":"doi:10.15398/jlm.v12i2.351","is_oa":true,"landing_page_url":"https://doi.org/10.15398/jlm.v12i2.351","pdf_url":"https://213.135.36.146/index.php/JLM/article/download/351/292","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,"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:pure.ed.ac.uk:openaire/0fed7820-6434-4cd7-8a9c-b41a2d2dc317","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/0fed7820-6434-4cd7-8a9c-b41a2d2dc317","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Haley, C, Ponti, E M & Goldwater, S 2024, 'Corpus-based measures discriminate inflection and derivation cross-linguistically', Journal of Language Modelling, vol. 12, no. 2, pp. 477-529. https://doi.org/10.15398/jlm.v12i2.351","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:doaj.org/article:a5170829cecb4147bc37e50f83a2f986","is_oa":true,"landing_page_url":"https://doaj.org/article/a5170829cecb4147bc37e50f83a2f986","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,"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 12, Iss 2 (2024)","raw_type":"article"},{"id":"pmh:oai:pure.ed.ac.uk:publications/0fed7820-6434-4cd7-8a9c-b41a2d2dc317","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/files/484229788/HaleyEtalJLM2024Corpus-basedMeasuresDiscriminate.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"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":"Haley, C, Ponti, E M & Goldwater, S 2024, 'Corpus-based measures discriminate inflection and derivation cross-linguistically', Journal of Language Modelling, vol. 12, no. 2, pp. 477-529. https://doi.org/10.15398/jlm.v12i2.351","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.15398/jlm.v12i2.351","is_oa":true,"landing_page_url":"https://doi.org/10.15398/jlm.v12i2.351","pdf_url":"https://213.135.36.146/index.php/JLM/article/download/351/292","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,"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":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7200000286102295}],"awards":[{"id":"https://openalex.org/G2527567836","display_name":"UKRI Centre for Doctoral Training in Natural Language Processing","funder_award_id":"EP/S022481/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G373773752","display_name":null,"funder_award_id":"EP/S022481/1","funder_id":"https://openalex.org/F4320314731","funder_display_name":"UK Research and Innovation"},{"id":"https://openalex.org/G581313191","display_name":null,"funder_award_id":"EP/T022159/","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G7002347110","display_name":"Cambridge Service for Data Driven Discovery (CSD3) - A National Data Intensive Science Cloud for Converged Simulation, AI & Analytics","funder_award_id":"EP/T022159/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320312927","display_name":"Dell EMC","ror":"https://ror.org/05rejmm18"},{"id":"https://openalex.org/F4320314731","display_name":"UK Research and Innovation","ror":"https://ror.org/001aqnf71"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"},{"id":"https://openalex.org/F4320334632","display_name":"Science and Technology Facilities Council","ror":"https://ror.org/057g20z61"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4405290311.pdf","grobid_xml":"https://content.openalex.org/works/W4405290311.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W153544860","https://openalex.org/W2014616736","https://openalex.org/W2250539671","https://openalex.org/W2294970769","https://openalex.org/W2493916176","https://openalex.org/W2570821393","https://openalex.org/W2756533552","https://openalex.org/W2787518295","https://openalex.org/W2791086851","https://openalex.org/W2798549337","https://openalex.org/W2888844359","https://openalex.org/W2963341956","https://openalex.org/W2963560804","https://openalex.org/W3034786567","https://openalex.org/W3035102548","https://openalex.org/W3035305735","https://openalex.org/W3035390927","https://openalex.org/W3104100020","https://openalex.org/W3185515067","https://openalex.org/W3205127767","https://openalex.org/W4237345350","https://openalex.org/W4238598663","https://openalex.org/W4298419326","https://openalex.org/W4321522319","https://openalex.org/W4390166905"],"related_works":["https://openalex.org/W2055902791","https://openalex.org/W2031827091","https://openalex.org/W1545736047","https://openalex.org/W4255541255","https://openalex.org/W2064751275","https://openalex.org/W4300462348","https://openalex.org/W75369696","https://openalex.org/W2624014444","https://openalex.org/W2510117412","https://openalex.org/W58877236"],"abstract_inverted_index":{"In":[0,37,73],"morphology,":[1],"a":[2,12,50,55,62,105,158,170,236],"distinction":[3,17],"is":[4],"commonly":[5],"drawn":[6],"between":[7,215,230],"inflection":[8,123,140,176,189],"and":[9,69,80,93,96,124,141,152,201,217],"derivation.":[10],"However,":[11],"precise":[13],"definition":[14],"of":[15,49,71,83,107,117,120,139,150,160,175,196,198,213],"this":[16,38,84],"which":[18,45,177],"reflects":[19],"the":[20,47,67,78,81,118,137,183,211,226,231],"way":[21,172],"it":[22],"manifests":[23],"across":[24,86,157],"languages":[25],"remains":[26],"elusive":[27],"within":[28],"linguistic":[29,184],"theory,":[30],"typically":[31],"being":[32],"based":[33],"on":[34,104],"subjective":[35],"tests.":[36],"study,":[39],"we":[40,75,110,113],"present":[41],"4":[42,130],"quantitative":[43,171],"measures":[44,166,209],"use":[46,164],"statistics":[48],"raw":[51],"text":[52],"corpus":[53],"in":[54,126,148,169,182,194],"language":[56],"to":[57,59,167],"estimate":[58],"what":[60],"extent":[61],"given":[63],"morphological":[64],"construction":[65],"changes":[66],"form":[68,151,200],"distribution":[70,153],"lexemes.":[72,87],"particular,":[74],"measure":[76],"both":[77],"average":[79],"variance":[82],"change":[85],"Crucially,":[88],"distributional":[89],"information":[90],"captures":[91],"syntactic":[92],"semantic":[94],"properties":[95,197],"can":[97,114],"be":[98],"operationalised":[99],"by":[100],"word":[101],"embeddings.":[102],"Based":[103],"sample":[106],"26":[108],"languages,":[109],"find":[111,204],"that":[112,136,154,205],"reconstruct":[115],"89\u00b11%":[116],"classification":[119],"constructions":[121,224],"into":[122],"derivation":[125,142],"UniMorph":[127],"using":[128],"our":[129,165],"measures,":[131],"providing":[132],"large-scale":[133],"cross-linguistic":[134],"evidence":[135],"concepts":[138],"are":[143,221],"associated":[144],"with":[145],"measurable":[146],"signatures":[147],"terms":[149,195],"behave":[155],"consistently":[156],"variety":[159],"languages.":[161],"We":[162,203],"also":[163],"identify":[168],"whether":[173],"categories":[174],"have":[178],"been":[179],"considered":[180],"noncanonical":[181],"literature,":[185],"such":[186],"as":[187],"inherent":[188],"or":[190],"transpositions,":[191],"appear":[192],"so":[193],"their":[199],"distribution.":[202],"while":[206],"combining":[207],"multiple":[208],"reduces":[210],"amount":[212],"overlap":[214],"inflectional":[216],"derivational":[218],"constructions,":[219],"there":[220],"still":[222],"many":[223],"near":[225],"model\u2019s":[227],"decision":[228],"boundary":[229],"two":[232],"categories.":[233],"This":[234],"indicates":[235],"gradient,":[237],"rather":[238],"than":[239],"categorical,":[240],"distinction.":[241]},"counts_by_year":[],"updated_date":"2026-08-29T07:29:34.045763","created_date":"2025-10-10T00:00:00"}