{"id":"https://openalex.org/W2798924688","doi":"https://doi.org/10.18653/v1/p18-2001","title":"Continuous Learning in a Hierarchical Multiscale Neural Network","display_name":"Continuous Learning in a Hierarchical Multiscale Neural Network","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2798924688","doi":"https://doi.org/10.18653/v1/p18-2001","mag":"2798924688"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p18-2001","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-2001","pdf_url":"https://www.aclweb.org/anthology/P18-2001.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":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P18-2001.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078865608","display_name":"Thomas Wolf","orcid":"https://orcid.org/0000-0002-7134-7314"},"institutions":[{"id":"https://openalex.org/I198945027","display_name":"Central European University","ror":"https://ror.org/02zx40v98","country_code":"AT","type":"education","lineage":["https://openalex.org/I198945027"]},{"id":"https://openalex.org/I4210136376","display_name":"FACE Foundation","ror":"https://ror.org/04121g745","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210136376"]},{"id":"https://openalex.org/I4387154989","display_name":"Hugging Face","ror":"https://ror.org/02grspc61","country_code":null,"type":"company","lineage":["https://openalex.org/I4387154989"]}],"countries":["AT","US"],"is_corresponding":true,"raw_author_name":"Thomas Wolf","raw_affiliation_strings":["Hugging Face Inc. 81 Prospect St. Brooklyn, New York 11201, USA","Central European University, Vienna, Austria"],"affiliations":[{"raw_affiliation_string":"Hugging Face Inc. 81 Prospect St. Brooklyn, New York 11201, USA","institution_ids":["https://openalex.org/I4210136376","https://openalex.org/I4387154989"]},{"raw_affiliation_string":"Central European University, Vienna, Austria","institution_ids":["https://openalex.org/I198945027"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038505596","display_name":"Julien Chaumond","orcid":"https://orcid.org/0000-0003-3188-1616"},"institutions":[{"id":"https://openalex.org/I4387154989","display_name":"Hugging Face","ror":"https://ror.org/02grspc61","country_code":null,"type":"company","lineage":["https://openalex.org/I4387154989"]},{"id":"https://openalex.org/I4210136376","display_name":"FACE Foundation","ror":"https://ror.org/04121g745","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210136376"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Julien Chaumond","raw_affiliation_strings":["Hugging Face Inc. 81 Prospect St. Brooklyn, New York 11201, USA"],"affiliations":[{"raw_affiliation_string":"Hugging Face Inc. 81 Prospect St. Brooklyn, New York 11201, USA","institution_ids":["https://openalex.org/I4210136376","https://openalex.org/I4387154989"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009717413","display_name":"Cl\u00e9ment Delangue","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136376","display_name":"FACE Foundation","ror":"https://ror.org/04121g745","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210136376"]},{"id":"https://openalex.org/I4387154989","display_name":"Hugging Face","ror":"https://ror.org/02grspc61","country_code":null,"type":"company","lineage":["https://openalex.org/I4387154989"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Clement Delangue","raw_affiliation_strings":["Hugging Face Inc. 81 Prospect St. Brooklyn, New York 11201, USA"],"affiliations":[{"raw_affiliation_string":"Hugging Face Inc. 81 Prospect St. Brooklyn, New York 11201, USA","institution_ids":["https://openalex.org/I4210136376","https://openalex.org/I4387154989"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5078865608"],"corresponding_institution_ids":["https://openalex.org/I198945027","https://openalex.org/I4210136376","https://openalex.org/I4387154989"],"apc_list":null,"apc_paid":null,"fwci":0.59568738,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.71816491,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"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":0.9988999962806702,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9986000061035156,"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/forgetting","display_name":"Forgetting","score":0.7875944375991821},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6902514696121216},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5812808275222778},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5588417053222656},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5560968518257141},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5341858863830566},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5116119980812073},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.48336261510849},{"id":"https://openalex.org/keywords/sequence-learning","display_name":"Sequence learning","score":0.4481451213359833},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4423426687717438},{"id":"https://openalex.org/keywords/consolidation","display_name":"Consolidation (business)","score":0.4302200675010681},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3631557822227478}],"concepts":[{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.7875944375991821},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6902514696121216},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5812808275222778},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5588417053222656},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5560968518257141},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5341858863830566},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5116119980812073},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.48336261510849},{"id":"https://openalex.org/C40506919","wikidata":"https://www.wikidata.org/wiki/Q7452469","display_name":"Sequence learning","level":2,"score":0.4481451213359833},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4423426687717438},{"id":"https://openalex.org/C2776014549","wikidata":"https://www.wikidata.org/wiki/Q3050847","display_name":"Consolidation (business)","level":2,"score":0.4302200675010681},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3631557822227478},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","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},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/p18-2001","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-2001","pdf_url":"https://www.aclweb.org/anthology/P18-2001.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":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1805.05758","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1805.05758","pdf_url":"https://arxiv.org/pdf/1805.05758","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":"","raw_type":"text"},{"id":"mag:2798924688","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1805.05758","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1805.05758","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1805.05758","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.18653/v1/p18-2001","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-2001","pdf_url":"https://www.aclweb.org/anthology/P18-2001.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":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2798924688.pdf","grobid_xml":"https://content.openalex.org/works/W2798924688.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W1575384945","https://openalex.org/W1843891098","https://openalex.org/W2148654448","https://openalex.org/W2251222643","https://openalex.org/W2341401723","https://openalex.org/W2342395274","https://openalex.org/W2409744450","https://openalex.org/W2423581336","https://openalex.org/W2427497464","https://openalex.org/W2510842514","https://openalex.org/W2525332836","https://openalex.org/W2606347107","https://openalex.org/W2743945814","https://openalex.org/W2753160622","https://openalex.org/W2757047188","https://openalex.org/W2784121710","https://openalex.org/W2787560479","https://openalex.org/W2950527759","https://openalex.org/W2950635152","https://openalex.org/W2964308564"],"related_works":["https://openalex.org/W2964301998","https://openalex.org/W2083227311","https://openalex.org/W3137320761","https://openalex.org/W3037150611","https://openalex.org/W2610990758","https://openalex.org/W2019165547","https://openalex.org/W3094559936","https://openalex.org/W2963982496","https://openalex.org/W2963627187","https://openalex.org/W1608668970","https://openalex.org/W2976768568","https://openalex.org/W3084020051","https://openalex.org/W1546029411","https://openalex.org/W3107728769","https://openalex.org/W2973077827","https://openalex.org/W2751528152","https://openalex.org/W2966626695","https://openalex.org/W2963600139","https://openalex.org/W1596473495","https://openalex.org/W2951663767"],"abstract_inverted_index":{"We":[0,24,78],"reformulate":[1],"the":[2,39,55,58,66,69],"problem":[3],"of":[4,9,42,57,68],"encoding":[5],"a":[6,10,13,20,26,43,63,84],"multi-scale":[7,28],"representation":[8],"sequence":[11],"in":[12,19,31,38,54,73,90],"language":[14,29],"model":[15,30],"by":[16,61],"casting":[17],"it":[18],"continuous":[21,92],"learning":[22,93],"framework.":[23,94],"propose":[25],"hierarchical":[27],"which":[32],"short":[33],"time-scale":[34,50],"dependencies":[35,51],"are":[36,52],"encoded":[37,53],"hidden":[40],"state":[41],"lower-level":[44,59,70],"recurrent":[45],"neural":[46,71],"network":[47,60,72],"while":[48],"longer":[49],"dynamic":[56],"having":[62],"meta-learner":[64],"update":[65],"weights":[67,81],"an":[74],"online":[75],"meta-learning":[76],"fashion.":[77],"use":[79],"elastic":[80],"consolidation":[82],"as":[83],"higher-level":[85],"to":[86],"prevent":[87],"catastrophic":[88],"forgetting":[89],"our":[91]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}