{"id":"https://openalex.org/W3015766957","doi":"https://doi.org/10.48550/arxiv.2004.03032","title":"A Systematic Analysis of Morphological Content in BERT Models for Multiple Languages","display_name":"A Systematic Analysis of Morphological Content in BERT Models for Multiple Languages","publication_year":2020,"publication_date":"2020-04-06","ids":{"openalex":"https://openalex.org/W3015766957","doi":"https://doi.org/10.48550/arxiv.2004.03032","mag":"3015766957"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2004.03032","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.03032","pdf_url":"https://arxiv.org/pdf/2004.03032","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2004.03032","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Edmiston, Daniel","orcid":null,"observed_orcids":[]},"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":true,"raw_author_name":"Edmiston, Daniel","raw_affiliation_strings":["University of Chicago (  )"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chicago (  )","institution_ids":["https://openalex.org/I40347166"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I40347166"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.7939000129699707,"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/T10028","display_name":"Topic Modeling","score":0.7939000129699707,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.18230000138282776,"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/T10034","display_name":"Syntax, Semantics, Linguistic Variation","score":0.006300000008195639,"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/bert","display_name":"BERT","score":0.8180000185966492},{"id":"https://openalex.org/keywords/morphological-features","display_name":"morphological features","score":0.9100000262260437},{"id":"https://openalex.org/keywords/morphological-ambiguity","display_name":"morphological ambiguity","score":0.6349999904632568},{"id":"https://openalex.org/keywords/subject-verb-agreement","display_name":"subject-verb agreement","score":0.7710000276565552},{"id":"https://openalex.org/keywords/attention-allocation","display_name":"attention allocation","score":0.4390000104904175},{"id":"https://openalex.org/keywords/multilingual-language-models","display_name":"multilingual language models","score":0.7059999704360962},{"id":"https://openalex.org/keywords/european-languages","display_name":"European languages","score":0.7089999914169312},{"id":"https://openalex.org/keywords/contextualized-embeddings","display_name":"contextual embeddings","score":0.5040000081062317}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.673930823802948},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5720887780189514},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5552376508712769},{"id":"https://openalex.org/C2776397901","wikidata":"https://www.wikidata.org/wiki/Q24905","display_name":"Verb","level":2,"score":0.48007044196128845},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46935945749282837},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.4629564881324768},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4609900116920471},{"id":"https://openalex.org/C13336665","wikidata":"https://www.wikidata.org/wiki/Q125977","display_name":"Vector space","level":2,"score":0.431303471326828},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4257630705833435},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.30092912912368774},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.11555010080337524},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07147172093391418},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2004.03032","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.03032","pdf_url":"https://arxiv.org/pdf/2004.03032","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2004.03032","doi":"https://doi.org/10.48550/arxiv.2004.03032","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2004.03032","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2004.03032","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.03032","pdf_url":"https://arxiv.org/pdf/2004.03032","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"score":0.7900000214576721,"id":"https://metadata.un.org/sdg/4","display_name":"Quality education"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W38462120","https://openalex.org/W79543249","https://openalex.org/W2017946383","https://openalex.org/W2064675550","https://openalex.org/W2139907445","https://openalex.org/W2150087485","https://openalex.org/W2250263931","https://openalex.org/W2251650669","https://openalex.org/W2264869955","https://openalex.org/W2299976354","https://openalex.org/W2529763891","https://openalex.org/W2549835527","https://openalex.org/W2562402330","https://openalex.org/W2579343286","https://openalex.org/W2605717780","https://openalex.org/W2626778328","https://openalex.org/W2787560479","https://openalex.org/W2792073421","https://openalex.org/W2805116303","https://openalex.org/W2910243263","https://openalex.org/W2946359678","https://openalex.org/W2946417913","https://openalex.org/W2946676565","https://openalex.org/W2948771346","https://openalex.org/W2950405925","https://openalex.org/W2951286828","https://openalex.org/W2952718809","https://openalex.org/W2953337107","https://openalex.org/W2963341956","https://openalex.org/W2964222268","https://openalex.org/W2965647350","https://openalex.org/W2986154550","https://openalex.org/W2988304195","https://openalex.org/W2995856824","https://openalex.org/W2996400930","https://openalex.org/W3006881356"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W2153749698","https://openalex.org/W2345479200","https://openalex.org/W2183306018","https://openalex.org/W2849310602","https://openalex.org/W3006008237","https://openalex.org/W2163511125","https://openalex.org/W2356312238","https://openalex.org/W2610352806","https://openalex.org/W2901841427"],"abstract_inverted_index":{"This":[0],"work":[1],"describes":[2],"experiments":[3,55],"which":[4,24],"probe":[5],"the":[6,21,29,40,78],"hidden":[7],"representations":[8,42],"of":[9,31,46,81],"several":[10],"BERT-style":[11],"models":[12,49,85],"for":[13,50],"morphological":[14,32,74,89],"content.":[15],"The":[16,54],"goal":[17],"is":[18],"to":[19,23,86,105],"examine":[20],"extent":[22],"discrete":[25],"linguistic":[26],"structure,":[27],"in":[28,39,91,107],"form":[30],"features":[33],"and":[34,43,97],"feature":[35,75],"values,":[36],"presents":[37],"itself":[38],"vector":[41],"attention":[44,101],"distributions":[45],"pre-trained":[47],"language":[48],"five":[51],"European":[52],"languages.":[53],"contained":[56],"herein":[57],"show":[58],"that":[59],"(i)":[60],"Transformer":[61],"architectures":[62],"largely":[63],"partition":[64],"their":[65],"embedding":[66],"space":[67],"into":[68],"convex":[69],"sub-regions":[70],"highly":[71],"correlated":[72],"with":[73],"value,":[76],"(ii)":[77],"contextualized":[79],"nature":[80],"transformer":[82],"embeddings":[83],"allows":[84],"distinguish":[87],"ambiguous":[88],"forms":[90],"many,":[92],"but":[93],"not":[94],"all":[95],"cases,":[96],"(iii)":[98],"very":[99],"specific":[100],"head/layer":[102],"combinations":[103],"appear":[104],"hone":[106],"on":[108],"subject-verb":[109],"agreement.":[110]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":5}],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2020-04-17T00:00:00"}