{"id":"https://openalex.org/W4385570444","doi":"https://doi.org/10.18653/v1/2023.findings-acl.132","title":"Nonparametric Masked Language Modeling","display_name":"Nonparametric Masked Language Modeling","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4385570444","doi":"https://doi.org/10.18653/v1/2023.findings-acl.132"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2023.findings-acl.132","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.findings-acl.132","pdf_url":"https://aclanthology.org/2023.findings-acl.132.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2023","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2023.findings-acl.132.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039158419","display_name":"Sewon Min","orcid":null},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sewon Min","raw_affiliation_strings":["Meta AI","University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]},{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103238719","display_name":"Weijia Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weijia Shi","raw_affiliation_strings":["Meta AI","University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]},{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Mike Lewis","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mike Lewis","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065674779","display_name":"Xilun Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xilun Chen","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066873932","display_name":"Wen-tau Yih","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wen-tau Yih","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082305994","display_name":"Hannaneh Hajishirzi","orcid":"https://orcid.org/0000-0002-1055-6657"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]},{"id":"https://openalex.org/I4210140341","display_name":"Allen Institute","ror":"https://ror.org/03cpe7c52","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210140341"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hannaneh Hajishirzi","raw_affiliation_strings":["Allen Institute for AI","University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Allen Institute for AI","institution_ids":["https://openalex.org/I4210140341"]},{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067919401","display_name":"Luke Zettlemoyer","orcid":"https://orcid.org/0009-0008-8296-0764"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Luke Zettlemoyer","raw_affiliation_strings":["Meta AI","University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]},{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.3442,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.95706771,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2097","last_page":"2118"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9994999766349792,"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":0.9919000267982483,"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":0.8582572340965271},{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.7563679218292236},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6653082370758057},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6596599817276001},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6324078440666199},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.571111261844635},{"id":"https://openalex.org/keywords/nonparametric-statistics","display_name":"Nonparametric statistics","score":0.5531168580055237},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5390912890434265},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.4933682978153229},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.4533797800540924},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4472561180591583},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3770938813686371},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.13899093866348267},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.1205950677394867}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8582572340965271},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.7563679218292236},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6653082370758057},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6596599817276001},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6324078440666199},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.571111261844635},{"id":"https://openalex.org/C102366305","wikidata":"https://www.wikidata.org/wiki/Q1097688","display_name":"Nonparametric statistics","level":2,"score":0.5531168580055237},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5390912890434265},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.4933682978153229},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.4533797800540924},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4472561180591583},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3770938813686371},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.13899093866348267},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1205950677394867},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2023.findings-acl.132","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.findings-acl.132","pdf_url":"https://aclanthology.org/2023.findings-acl.132.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2023","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2023.findings-acl.132","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.findings-acl.132","pdf_url":"https://aclanthology.org/2023.findings-acl.132.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2023","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8500000238418579,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1488683580","display_name":null,"funder_award_id":"N00014\u201018\u20101\u20102670","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G3391801044","display_name":"CAREER: Knowledge-Rich Neural Text Comprehension and Reasoning","funder_award_id":"2044660","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3812534482","display_name":null,"funder_award_id":"N00014-18-1-2826","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G6570891669","display_name":null,"funder_award_id":"MURI N00014-18-1-2670","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320333591","display_name":"Multidisciplinary University Research Initiative","ror":null},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385570444.pdf"},"referenced_works_count":80,"referenced_works":["https://openalex.org/W36903255","https://openalex.org/W150793826","https://openalex.org/W1522301498","https://openalex.org/W2077815765","https://openalex.org/W2097074225","https://openalex.org/W2122196799","https://openalex.org/W2124509324","https://openalex.org/W2130158090","https://openalex.org/W2137419020","https://openalex.org/W2143345705","https://openalex.org/W2160660844","https://openalex.org/W2170240176","https://openalex.org/W2251939518","https://openalex.org/W2519314406","https://openalex.org/W2785611959","https://openalex.org/W2896457183","https://openalex.org/W2908743445","https://openalex.org/W2912924812","https://openalex.org/W2949380545","https://openalex.org/W2950729111","https://openalex.org/W2951434086","https://openalex.org/W2962916648","https://openalex.org/W2963339397","https://openalex.org/W2963537482","https://openalex.org/W2963932686","https://openalex.org/W2963967365","https://openalex.org/W2965373594","https://openalex.org/W2970476646","https://openalex.org/W2979826702","https://openalex.org/W2983915252","https://openalex.org/W2998702515","https://openalex.org/W3011411500","https://openalex.org/W3024786184","https://openalex.org/W3027879771","https://openalex.org/W3035390927","https://openalex.org/W3093517588","https://openalex.org/W3099700870","https://openalex.org/W3104748221","https://openalex.org/W3104929588","https://openalex.org/W3118027562","https://openalex.org/W3157700644","https://openalex.org/W3166986030","https://openalex.org/W3169483174","https://openalex.org/W3169937871","https://openalex.org/W3172943453","https://openalex.org/W3173777717","https://openalex.org/W3175627818","https://openalex.org/W3176119108","https://openalex.org/W3177415603","https://openalex.org/W4205694376","https://openalex.org/W4205857304","https://openalex.org/W4206778668","https://openalex.org/W4221155916","https://openalex.org/W4224308101","https://openalex.org/W4226082499","https://openalex.org/W4226146865","https://openalex.org/W4229005866","https://openalex.org/W4248694980","https://openalex.org/W4252076394","https://openalex.org/W4280525837","https://openalex.org/W4281629162","https://openalex.org/W4286909694","https://openalex.org/W4287111051","https://openalex.org/W4287827771","https://openalex.org/W4287854732","https://openalex.org/W4288087322","https://openalex.org/W4288089799","https://openalex.org/W4292779060","https://openalex.org/W4293138840","https://openalex.org/W4295312788","https://openalex.org/W4297808394","https://openalex.org/W4298183015","https://openalex.org/W4298345797","https://openalex.org/W4301243929","https://openalex.org/W4306801963","https://openalex.org/W4309217888","https://openalex.org/W4311642023","https://openalex.org/W4385572901","https://openalex.org/W4385573102","https://openalex.org/W4385574029"],"related_works":["https://openalex.org/W3107204728","https://openalex.org/W4287591324","https://openalex.org/W4226420367","https://openalex.org/W2980176872","https://openalex.org/W2962876041","https://openalex.org/W3090555870","https://openalex.org/W3108503355","https://openalex.org/W2249953602","https://openalex.org/W2801655600","https://openalex.org/W2268150819"],"abstract_inverted_index":{"Existing":[0],"language":[1,31],"models":[2],"(LMs)":[3],"predict":[4,19],"tokens":[5,21],"with":[6,37,70,103,115],"a":[7,10,38,45,56,59,71,106],"softmax":[8,36],"over":[9,41],"finite":[11],"vocabulary,":[12],"which":[13],"can":[14,66],"make":[15],"it":[16],"difficult":[17],"to":[18,78],"rare":[20,116,124],"or":[22,104,120,125],"phrases.":[23],"We":[24,62,132],"introduce":[25],"NPM,":[26],"the":[27,51,134],"first":[28],"nonparametric":[29,39],"masked":[30],"model":[32,135],"that":[33,64,95],"replaces":[34],"this":[35],"distribution":[40],"every":[42],"phrase":[43],"in":[44,50],"reference":[46],"corpus.":[47,61],"NPM":[48,65,96],"fills":[49],"[MASK]":[52],"solely":[53],"from":[54,58],"retrieving":[55],"token":[57],"text":[60],"show":[63],"be":[67],"efficiently":[68],"trained":[69],"contrastive":[72],"objective":[73],"and":[74,91,122,136],"an":[75],"in-batch":[76],"approximation":[77],"full":[79],"corpus":[80],"retrieval.":[81],"Zero-shot":[82],"evaluation":[83],"on":[84],"16":[85],"tasks":[86],"including":[87],"classification,":[88],"fact":[89],"probing":[90],"question":[92],"answering":[93],"demonstrates":[94],"outperforms":[97],"significantly":[98],"larger":[99],"parametric":[100],"models,":[101],"either":[102],"without":[105],"retrieve-and-generate":[107],"approach.":[108],"It":[109],"is":[110],"particularly":[111],"better":[112],"at":[113,138],"dealing":[114],"patterns":[117],"(word":[118],"senses":[119],"facts)":[121],"predicting":[123],"nearly":[126],"unseen":[127],"words":[128],"(e.g.,":[129],"non-Latin":[130],"script).":[131],"release":[133],"code":[137],"github.com/facebookresearch/NPM.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":8}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}