{"id":"https://openalex.org/W2972447203","doi":"https://doi.org/10.1162/tacl_a_00283","title":"<i>Tabula</i>Nearly<i>Rasa:</i>Probing the Linguistic Knowledge of Character-level Neural Language Models Trained on Unsegmented Text","display_name":"<i>Tabula</i>Nearly<i>Rasa:</i>Probing the Linguistic Knowledge of Character-level Neural Language Models Trained on Unsegmented Text","publication_year":2019,"publication_date":"2019-09-11","ids":{"openalex":"https://openalex.org/W2972447203","doi":"https://doi.org/10.1162/tacl_a_00283","mag":"2972447203"},"language":"en","primary_location":{"id":"doi:10.1162/tacl_a_00283","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00283","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00283/1923543/tacl_a_00283.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":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00283/1923543/tacl_a_00283.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007794565","display_name":"Michael Hahn","orcid":"https://orcid.org/0000-0003-4828-4834"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Michael Hahn","raw_affiliation_strings":["Stanford University","Stanford University, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Stanford University, United States","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038612405","display_name":"Marco Baroni","orcid":"https://orcid.org/0000-0001-5066-3580"},"institutions":[{"id":"https://openalex.org/I11932220","display_name":"Instituci\u00f3 Catalana de Recerca i Estudis Avan\u00e7ats","ror":"https://ror.org/0371hy230","country_code":"ES","type":"nonprofit","lineage":["https://openalex.org/I11932220"]},{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["ES","IL"],"is_corresponding":true,"raw_author_name":"Marco Baroni","raw_affiliation_strings":["Facebook AI Research, UPF Linguistics Department, Catalan Institution for Research and Advanced Studies","Facebook AI Research, UPF Linguistics Department, Catalan Institution for Research and Advanced Studies, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research, UPF Linguistics Department, Catalan Institution for Research and Advanced Studies","institution_ids":["https://openalex.org/I2252078561"]},{"raw_affiliation_string":"Facebook AI Research, UPF Linguistics Department, Catalan Institution for Research and Advanced Studies, Spain","institution_ids":["https://openalex.org/I11932220"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5007794565","https://openalex.org/A5038612405"],"corresponding_institution_ids":["https://openalex.org/I11932220","https://openalex.org/I2252078561","https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":0.7254,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.78930984,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"7","issue":null,"first_page":"467","last_page":"484"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998999834060669,"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":0.9966999888420105,"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/computer-science","display_name":"Computer science","score":0.8177152872085571},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6992724537849426},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.6384283304214478},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.6262625455856323},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6086235642433167},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5539301633834839},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5177382826805115},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.5072433352470398},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5070931911468506},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.42453524470329285},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.42081063985824585},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.41346442699432373}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8177152872085571},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6992724537849426},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.6384283304214478},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.6262625455856323},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6086235642433167},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5539301633834839},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5177382826805115},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5072433352470398},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5070931911468506},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.42453524470329285},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.42081063985824585},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41346442699432373},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1162/tacl_a_00283","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00283","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00283/1923543/tacl_a_00283.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:doaj.org/article:a88791791a77479eb6504d2852a10230","is_oa":true,"landing_page_url":"https://doaj.org/article/a88791791a77479eb6504d2852a10230","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Transactions of the Association for Computational Linguistics, Vol 7, Pp 467-484 (2019)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/tacl_a_00283","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00283","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00283/1923543/tacl_a_00283.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":[{"score":0.8600000143051147,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2972447203.pdf"},"referenced_works_count":81,"referenced_works":["https://openalex.org/W196214544","https://openalex.org/W331019419","https://openalex.org/W354650940","https://openalex.org/W591353820","https://openalex.org/W608050949","https://openalex.org/W653912306","https://openalex.org/W1522263329","https://openalex.org/W1527142120","https://openalex.org/W1550933260","https://openalex.org/W1579929927","https://openalex.org/W1614298861","https://openalex.org/W1722351164","https://openalex.org/W1810943226","https://openalex.org/W1938755728","https://openalex.org/W1971624066","https://openalex.org/W1988126949","https://openalex.org/W2018982897","https://openalex.org/W2020944885","https://openalex.org/W2029948425","https://openalex.org/W2038542953","https://openalex.org/W2064675550","https://openalex.org/W2085663684","https://openalex.org/W2104752510","https://openalex.org/W2108425242","https://openalex.org/W2110485445","https://openalex.org/W2124059530","https://openalex.org/W2126377586","https://openalex.org/W2141599568","https://openalex.org/W2148917251","https://openalex.org/W2166391802","https://openalex.org/W2167723982","https://openalex.org/W2168488947","https://openalex.org/W2176796957","https://openalex.org/W2255581062","https://openalex.org/W2292919134","https://openalex.org/W2295297373","https://openalex.org/W2346280181","https://openalex.org/W2480148714","https://openalex.org/W2507974895","https://openalex.org/W2510248383","https://openalex.org/W2515741950","https://openalex.org/W2531207078","https://openalex.org/W2531882892","https://openalex.org/W2549835527","https://openalex.org/W2559655401","https://openalex.org/W2561296568","https://openalex.org/W2563574619","https://openalex.org/W2579599705","https://openalex.org/W2605717780","https://openalex.org/W2606347107","https://openalex.org/W2759181158","https://openalex.org/W2767360697","https://openalex.org/W2781528640","https://openalex.org/W2788924045","https://openalex.org/W2792376130","https://openalex.org/W2799124508","https://openalex.org/W2803214681","https://openalex.org/W2883158411","https://openalex.org/W2884554299","https://openalex.org/W2888958984","https://openalex.org/W2889506631","https://openalex.org/W2900065283","https://openalex.org/W2905532018","https://openalex.org/W2905623858","https://openalex.org/W2911267749","https://openalex.org/W2949888546","https://openalex.org/W2953318277","https://openalex.org/W2963025830","https://openalex.org/W2963208801","https://openalex.org/W2963430224","https://openalex.org/W2963751529","https://openalex.org/W2964072233","https://openalex.org/W2964159778","https://openalex.org/W2964289395","https://openalex.org/W3105148948","https://openalex.org/W3140196993","https://openalex.org/W4210984920","https://openalex.org/W4241976975","https://openalex.org/W4252588748","https://openalex.org/W4299895104","https://openalex.org/W4387627350"],"related_works":["https://openalex.org/W4221161337","https://openalex.org/W88309612","https://openalex.org/W2896411932","https://openalex.org/W4386107059","https://openalex.org/W77769009","https://openalex.org/W1539050421","https://openalex.org/W2122691642","https://openalex.org/W2296152660","https://openalex.org/W3119155061","https://openalex.org/W4385452111"],"abstract_inverted_index":{"Recurrent":[0],"neural":[1],"networks":[2,77],"(RNNs)":[3],"have":[4],"reached":[5],"striking":[6],"performance":[7],"in":[8,18,62,150],"many":[9],"natural":[10],"language":[11,67,151],"processing":[12,23],"tasks.":[13],"This":[14],"has":[15],"renewed":[16],"interest":[17],"whether":[19],"these":[20],"generic":[21],"sequence":[22],"devices":[24],"are":[25,108],"inducing":[26],"genuine":[27],"linguistic":[28,59,91],"knowledge.":[29],"Nearly":[30],"all":[31],"current":[32],"analytical":[33],"studies,":[34],"however,":[35],"initialize":[36],"the":[37,58,137,142],"RNNs":[38,63,107],"with":[39,72],"a":[40,54,79],"vocabulary":[41],"of":[42,57,144],"known":[43],"words,":[44],"and":[45,81,115,123,153],"feed":[46],"them":[47],"tokenized":[48],"input":[49,70,97],"during":[50],"training.":[51],"We":[52],"present":[53],"multi-lingual":[55],"study":[56,135],"knowledge":[60],"encoded":[61],"trained":[64],"as":[65],"character-level":[66],"models,":[68],"on":[69,96],"data":[71],"word":[73,132,148],"boundaries":[74],"removed.":[75],"These":[76],"face":[78],"tougher":[80],"more":[82],"cognitively":[83],"realistic":[84],"task,":[85],"having":[86],"to":[87,111,127,130,139],"discover":[88],"any":[89],"useful":[90],"unit":[92],"from":[93],"scratch":[94],"based":[95],"statistics.":[98],"The":[99],"results":[100],"show":[101],"that":[102,118],"our":[103],"\u201cnear":[104],"tabula":[105],"rasa\u201d":[106],"mostly":[109],"able":[110],"solve":[112],"morphological,":[113],"syntactic":[114],"semantic":[116],"tasks":[117],"intuitively":[119],"presuppose":[120],"word-level":[121],"knowledge,":[122],"indeed":[124],"they":[125],"learned,":[126],"some":[128],"extent,":[129],"track":[131],"boundaries.":[133],"Our":[134],"opens":[136],"door":[138],"speculations":[140],"about":[141],"necessity":[143],"an":[145],"explicit,":[146],"rigid":[147],"lexicon":[149],"learning":[152],"usage.":[154]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1}],"updated_date":"2026-05-22T06:13:13.366637","created_date":"2019-09-19T00:00:00"}