{"id":"https://openalex.org/W3111869745","doi":"https://doi.org/10.1162/tacl_a_00365","title":"Morphology Matters: A Multilingual Language Modeling Analysis","display_name":"Morphology Matters: A Multilingual Language Modeling Analysis","publication_year":2021,"publication_date":"2021-03-17","ids":{"openalex":"https://openalex.org/W3111869745","doi":"https://doi.org/10.1162/tacl_a_00365","mag":"3111869745"},"language":"en","primary_location":{"id":"doi:10.1162/tacl_a_00365","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00365","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00365/1924158/tacl_a_00365.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00365/1924158/tacl_a_00365.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Hyunji Hayley Park","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hyunji Hayley Park","raw_affiliation_strings":["University of Illinois. hpark129@illinois.edu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois. hpark129@illinois.edu","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Katherine J. Zhang","orcid":null},"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":"Katherine J. Zhang","raw_affiliation_strings":["Carnegie Mellon University. kjzhang@cmu.edu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University. kjzhang@cmu.edu","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Coleman Haley","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Coleman Haley","raw_affiliation_strings":["Johns Hopkins University. chaley7@jhu.edu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University. chaley7@jhu.edu","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kenneth Steimel","orcid":null},"institutions":[{"id":"https://openalex.org/I55769427","display_name":"Indiana University \u2013 Purdue University Indianapolis","ror":"https://ror.org/05gxnyn08","country_code":"US","type":"education","lineage":["https://openalex.org/I55769427","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kenneth Steimel","raw_affiliation_strings":["Indiana University. ksteimel@iu.edu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indiana University. ksteimel@iu.edu","institution_ids":["https://openalex.org/I55769427"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Han Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Han Liu","raw_affiliation_strings":["University of Chicago. hanliu@uchicago.edu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chicago. hanliu@uchicago.edu","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"last","author":{"id":null,"display_name":"Lane Schwartz","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lane Schwartz","raw_affiliation_strings":["University of Illinois. lanes@illinois.edu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois. lanes@illinois.edu","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9534,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.78902994,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"9","issue":null,"first_page":"261","last_page":"276"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.3440999984741211,"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":0.3440999984741211,"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":0.17329999804496765,"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/T13629","display_name":"Text Readability and Simplification","score":0.07069999724626541,"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/language-model","display_name":"Language model","score":0.535099983215332},{"id":"https://openalex.org/keywords/morphology","display_name":"Morphology (biology)","score":0.5012000203132629},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.49149999022483826},{"id":"https://openalex.org/keywords/constructed-language","display_name":"Constructed language","score":0.2969000041484833},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.2754000127315521},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.2741999924182892}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8479999899864197},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6894000172615051},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5971999764442444},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.535099983215332},{"id":"https://openalex.org/C499950583","wikidata":"https://www.wikidata.org/wiki/Q183252","display_name":"Morphology (biology)","level":2,"score":0.5012000203132629},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.49149999022483826},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4772000014781952},{"id":"https://openalex.org/C94922259","wikidata":"https://www.wikidata.org/wiki/Q33215","display_name":"Constructed language","level":2,"score":0.2969000041484833},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2754000127315521},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.2741999924182892},{"id":"https://openalex.org/C75795011","wikidata":"https://www.wikidata.org/wiki/Q917904","display_name":"Typology","level":2,"score":0.2680000066757202},{"id":"https://openalex.org/C2985367798","wikidata":"https://www.wikidata.org/wiki/Q1346592","display_name":"Parallel corpora","level":3,"score":0.2653999924659729},{"id":"https://openalex.org/C165297611","wikidata":"https://www.wikidata.org/wiki/Q43249","display_name":"Morpheme","level":2,"score":0.26440000534057617},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.2522999942302704}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1162/tacl_a_00365","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00365","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00365/1924158/tacl_a_00365.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2012.06262","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2012.06262","pdf_url":"https://arxiv.org/pdf/2012.06262","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:doaj.org/article:dd9391075bdc424aa2b325a901723747","is_oa":false,"landing_page_url":"https://doaj.org/article/dd9391075bdc424aa2b325a901723747","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Transactions of the Association for Computational Linguistics, Vol 9, Pp 261-276 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/tacl_a_00365","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00365","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00365/1924158/tacl_a_00365.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W107550075","https://openalex.org/W153544860","https://openalex.org/W2007035566","https://openalex.org/W2014552602","https://openalex.org/W2041532239","https://openalex.org/W2053306448","https://openalex.org/W2110065044","https://openalex.org/W2252096090","https://openalex.org/W2890225082","https://openalex.org/W2892145626","https://openalex.org/W2953092638","https://openalex.org/W2962784628","https://openalex.org/W2963099225","https://openalex.org/W2963357986","https://openalex.org/W2963979492","https://openalex.org/W6600880057","https://openalex.org/W6680913097","https://openalex.org/W6691645747","https://openalex.org/W6691706656","https://openalex.org/W6713471092","https://openalex.org/W6727497285","https://openalex.org/W6734711280","https://openalex.org/W6740122878","https://openalex.org/W6749518548","https://openalex.org/W6751793318","https://openalex.org/W6751854987","https://openalex.org/W6753097580","https://openalex.org/W6755207826","https://openalex.org/W6763701032","https://openalex.org/W6766673545","https://openalex.org/W6776315367","https://openalex.org/W6777152735","https://openalex.org/W6783953245","https://openalex.org/W6788069494"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Prior":[1],"studies":[2],"in":[3,47,59,73],"multilingual":[4],"language":[5,131],"modeling":[6],"(e.g.,":[7],"Cotterell":[8],"et":[9,13],"al.,":[10,14],"2018;":[11],"Mielke":[12],"2019)":[15],"disagree":[16],"on":[17,130],"whether":[18],"or":[19],"not":[20],"inflectional":[21],"morphology":[22,129],"makes":[23],"languages":[24,49,65],"harder":[25],"to":[26,30,75],"model.":[27],"We":[28,38,57,79,99],"attempt":[29],"resolve":[31],"the":[32,124],"disagreement":[33],"and":[34,50,66,109,113,122],"extend":[35],"those":[36],"studies.":[37],"compile":[39],"a":[40,51,127],"larger":[41,52],"corpus":[42],"of":[43,54,70,126],"145":[44],"Bible":[45],"translations":[46],"92":[48],"number":[53],"typological":[55,61,77],"features.1":[56],"fill":[58],"missing":[60],"data":[62],"for":[63],"several":[64,82],"consider":[67],"corpus-based":[68],"measures":[69,84],"morphological":[71,83],"complexity":[72],"addition":[74],"expert-produced":[76],"features.":[78],"find":[80,114],"that":[81,115],"are":[85,94],"significantly":[86],"associated":[87],"with":[88,96],"higher":[89],"surprisal":[90],"when":[91],"LSTM":[92],"models":[93],"trained":[95],"BPE-segmented":[97],"data.":[98],"also":[100],"investigate":[101],"linguistically":[102],"motivated":[103],"subword":[104],"segmentation":[105,117],"strategies":[106,118],"like":[107],"Morfessor":[108],"Finite-State":[110],"Transducers":[111],"(FSTs)":[112],"these":[116],"yield":[119],"better":[120],"performance":[121],"reduce":[123],"impact":[125],"language\u2019s":[128],"modeling.":[132]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2020-12-21T00:00:00"}