{"id":"https://openalex.org/W3157700644","doi":"https://doi.org/10.1162/tacl_a_00371","title":"Adaptive Semiparametric Language Models","display_name":"Adaptive Semiparametric Language Models","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3157700644","doi":"https://doi.org/10.1162/tacl_a_00371","mag":"3157700644"},"language":"en","primary_location":{"id":"doi:10.1162/tacl_a_00371","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00371","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00371/1924150/tacl_a_00371.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_00371/1924150/tacl_a_00371.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060347694","display_name":"Dani Yogatama","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210113297","display_name":"Google (United Kingdom)","ror":"https://ror.org/024bc3e07","country_code":"GB","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210113297","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Dani Yogatama","raw_affiliation_strings":["DeepMind, London, United Kingdom. dyogatama@google.com"],"affiliations":[{"raw_affiliation_string":"DeepMind, London, United Kingdom. dyogatama@google.com","institution_ids":["https://openalex.org/I4210113297","https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038992613","display_name":"Cyprien de Masson d\u2019Autume","orcid":"https://orcid.org/0000-0002-4183-9641"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Cyprien de Masson d\u2019Autume","raw_affiliation_strings":["DeepMind, London, United Kingdom. cyprien@google.com"],"affiliations":[{"raw_affiliation_string":"DeepMind, London, United Kingdom. cyprien@google.com","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014554970","display_name":"Lingpeng Kong","orcid":"https://orcid.org/0000-0002-9033-2724"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Lingpeng Kong","raw_affiliation_strings":["DeepMind, London, United Kingdom. lingpenk@google.com"],"affiliations":[{"raw_affiliation_string":"DeepMind, London, United Kingdom. lingpenk@google.com","institution_ids":["https://openalex.org/I4210090411"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5014554970","https://openalex.org/A5038992613","https://openalex.org/A5060347694"],"corresponding_institution_ids":["https://openalex.org/I4210090411","https://openalex.org/I4210113297"],"apc_list":null,"apc_paid":null,"fwci":6.7987,"has_fulltext":true,"cited_by_count":54,"citation_normalized_percentile":{"value":0.97358094,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"9","issue":null,"first_page":"362","last_page":"373"},"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":0.9991999864578247,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9937000274658203,"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":0.9026786088943481},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6235212683677673},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6092215776443481},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.532558798789978},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5182014107704163},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.4110621511936188},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40471285581588745},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3357148766517639},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3255773186683655}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9026786088943481},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6235212683677673},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6092215776443481},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.532558798789978},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5182014107704163},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.4110621511936188},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40471285581588745},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3357148766517639},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3255773186683655},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1162/tacl_a_00371","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00371","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00371/1924150/tacl_a_00371.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:4d6a91c6e8ff40bfb1af0dd1fd3c888a","is_oa":true,"landing_page_url":"https://doaj.org/article/4d6a91c6e8ff40bfb1af0dd1fd3c888a","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 9, Pp 362-373 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/tacl_a_00371","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00371","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00371/1924150/tacl_a_00371.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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3157700644.pdf","grobid_xml":"https://content.openalex.org/works/W3157700644.grobid-xml"},"referenced_works_count":59,"referenced_works":["https://openalex.org/W2073667556","https://openalex.org/W2121853679","https://openalex.org/W2571859396","https://openalex.org/W2583010282","https://openalex.org/W2913344689","https://openalex.org/W2936652946","https://openalex.org/W2948743095","https://openalex.org/W2962964385","https://openalex.org/W2963018920","https://openalex.org/W2963034893","https://openalex.org/W2963149635","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963494889","https://openalex.org/W2963631907","https://openalex.org/W2963824800","https://openalex.org/W2963938518","https://openalex.org/W2964110616","https://openalex.org/W2964121744","https://openalex.org/W2964318358","https://openalex.org/W2970172215","https://openalex.org/W2970476646","https://openalex.org/W2973727699","https://openalex.org/W2994673210","https://openalex.org/W2995154514","https://openalex.org/W2995575179","https://openalex.org/W3007672467","https://openalex.org/W3015468748","https://openalex.org/W3034696692","https://openalex.org/W3091627448","https://openalex.org/W3098903812","https://openalex.org/W3100714086","https://openalex.org/W3102839769","https://openalex.org/W3125056032","https://openalex.org/W3125238517","https://openalex.org/W3126425262","https://openalex.org/W6631190155","https://openalex.org/W6726378182","https://openalex.org/W6727099177","https://openalex.org/W6729239390","https://openalex.org/W6731780175","https://openalex.org/W6732703391","https://openalex.org/W6739901393","https://openalex.org/W6743794615","https://openalex.org/W6744707562","https://openalex.org/W6754905691","https://openalex.org/W6755207826","https://openalex.org/W6761380950","https://openalex.org/W6767278183","https://openalex.org/W6767997687","https://openalex.org/W6770251742","https://openalex.org/W6770813465","https://openalex.org/W6771626834","https://openalex.org/W6774222543","https://openalex.org/W6777399232","https://openalex.org/W6778883912","https://openalex.org/W6783813245","https://openalex.org/W6783944145","https://openalex.org/W6784180246"],"related_works":["https://openalex.org/W3049463507","https://openalex.org/W2936497627","https://openalex.org/W4288365749","https://openalex.org/W3013624417","https://openalex.org/W4287826556","https://openalex.org/W4287598411","https://openalex.org/W3098382480","https://openalex.org/W3198458223","https://openalex.org/W4288267738","https://openalex.org/W3126642501"],"abstract_inverted_index":{"Abstract":[0],"We":[1,53],"present":[2],"a":[3,8,14,17,44,55,66],"language":[4,102],"model":[5,27,72],"that":[6],"combines":[7],"large":[9],"parametric":[10],"neural":[11],"network":[12],"(i.e.,":[13],"transformer)":[15],"with":[16],"non-parametric":[18],"episodic":[19],"memory":[20,41,82],"component":[21],"in":[22],"an":[23,89],"integrated":[24],"architecture.":[25],"Our":[26],"uses":[28],"extended":[29],"short-term":[30,78],"context":[31],"by":[32,42],"caching":[33],"local":[34,76],"hidden":[35],"states\u2014similar":[36],"to":[37,58,64,73,113],"transformer-XL\u2014and":[38],"global":[39],"long-term":[40,81],"retrieving":[43],"set":[45],"of":[46,86,108],"nearest":[47],"neighbor":[48],"tokens":[49],"at":[50],"each":[51],"timestep.":[52],"design":[54],"gating":[56],"function":[57],"adaptively":[59],"combine":[60],"multiple":[61],"information":[62],"sources":[63],"make":[65],"prediction.":[67],"This":[68],"mechanism":[69],"allows":[70],"the":[71,95,106],"use":[74],"either":[75],"context,":[77],"memory,":[79],"or":[80],"(or":[83],"any":[84],"combination":[85],"them)":[87],"on":[88,94,98],"ad":[90],"hoc":[91],"basis":[92],"depending":[93],"context.":[96],"Experiments":[97],"word-based":[99],"and":[100],"character-based":[101],"modeling":[103],"datasets":[104],"demonstrate":[105],"efficacy":[107],"our":[109],"proposed":[110],"method":[111],"compared":[112],"strong":[114],"baselines.":[115]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":22},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}