{"id":"https://openalex.org/W3205374543","doi":"https://doi.org/10.18653/v1/2022.acl-long.325","title":"Large Scale Substitution-based Word Sense Induction","display_name":"Large Scale Substitution-based Word Sense Induction","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W3205374543","doi":"https://doi.org/10.18653/v1/2022.acl-long.325","mag":"3205374543"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2022.acl-long.325","doi":"https://doi.org/10.18653/v1/2022.acl-long.325","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.acl-long.325","pdf_url":"https://aclanthology.org/2022.acl-long.325.pdf","source":{"id":"https://openalex.org/S4363608652","display_name":"Annual Meeting of the Association for Computational Linguistics (ACL)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2022.acl-long.325.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035283714","display_name":"Matan Eyal","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210156221","display_name":"Allen Institute for Artificial Intelligence","ror":"https://ror.org/05w520734","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210156221"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matan Eyal","raw_affiliation_strings":["Allen Institute for AI , Israel","Allen Institute for AI, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Allen Institute for AI , Israel","institution_ids":["https://openalex.org/I4210156221"]},{"raw_affiliation_string":"Allen Institute for AI, Israel","institution_ids":["https://openalex.org/I4210156221"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046322107","display_name":"Shoval Sadde","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210156221","display_name":"Allen Institute for Artificial Intelligence","ror":"https://ror.org/05w520734","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210156221"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shoval Sadde","raw_affiliation_strings":["Allen Institute for AI , Israel","Allen Institute for AI, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Allen Institute for AI , Israel","institution_ids":["https://openalex.org/I4210156221"]},{"raw_affiliation_string":"Allen Institute for AI, Israel","institution_ids":["https://openalex.org/I4210156221"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110854695","display_name":"Hillel Taub-Tabib","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210156221","display_name":"Allen Institute for Artificial Intelligence","ror":"https://ror.org/05w520734","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210156221"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hillel Taub-Tabib","raw_affiliation_strings":["Allen Institute for AI , Israel","Allen Institute for AI, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Allen Institute for AI , Israel","institution_ids":["https://openalex.org/I4210156221"]},{"raw_affiliation_string":"Allen Institute for AI, Israel","institution_ids":["https://openalex.org/I4210156221"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028476919","display_name":"Yoav Goldberg","orcid":"https://orcid.org/0000-0002-6497-829X","observed_orcids":["https://orcid.org/0000-0002-6497-829X"]},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]},{"id":"https://openalex.org/I4210156221","display_name":"Allen Institute for Artificial Intelligence","ror":"https://ror.org/05w520734","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210156221"]}],"countries":["IL","US"],"is_corresponding":false,"raw_author_name":"Yoav Goldberg","raw_affiliation_strings":["Allen Institute for AI , Israel","Bar Ilan University , Ramat-Gan , Israel","Allen Institute for AI, Israel","Bar Ilan University, Ramat-Gan, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Allen Institute for AI , Israel","institution_ids":["https://openalex.org/I4210156221"]},{"raw_affiliation_string":"Bar Ilan University , Ramat-Gan , Israel","institution_ids":["https://openalex.org/I13955877"]},{"raw_affiliation_string":"Allen Institute for AI, Israel","institution_ids":["https://openalex.org/I4210156221"]},{"raw_affiliation_string":"Bar Ilan University, Ramat-Gan, Israel","institution_ids":["https://openalex.org/I13955877"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2435,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.81796489,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"4738","last_page":"4752"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.8306000232696533,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.8306000232696533,"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/T10028","display_name":"Topic Modeling","score":0.15770000219345093,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.0026000000070780516,"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/word-sense-induction","display_name":"word sense induction","score":0.9900000095367432},{"id":"https://openalex.org/keywords/word-sense-disambiguation","display_name":"word sense disambiguation","score":0.9350000023841858},{"id":"https://openalex.org/keywords/masked-language-models","display_name":"masked language models","score":0.9449999928474426},{"id":"https://openalex.org/keywords/sense-inventory","display_name":"sense inventory","score":0.7720000147819519},{"id":"https://openalex.org/keywords/static-word-embeddings","display_name":"static word embeddings","score":0.7360000014305115},{"id":"https://openalex.org/keywords/outlier-detection","display_name":"outlier detection","score":0.9570000171661377},{"id":"https://openalex.org/keywords/wikipedia","display_name":"Wikipedia","score":0.5199999809265137},{"id":"https://openalex.org/keywords/scientific-domains","display_name":"scientific domains","score":0.7099999785423279}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7718188166618347},{"id":"https://openalex.org/C143141573","wikidata":"https://www.wikidata.org/wiki/Q7450971","display_name":"Sense (electronics)","level":2,"score":0.7160929441452026},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.703718900680542},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6602063775062561},{"id":"https://openalex.org/C51646954","wikidata":"https://www.wikidata.org/wiki/Q48522","display_name":"Word-sense disambiguation","level":3,"score":0.6558136343955994},{"id":"https://openalex.org/C2778220771","wikidata":"https://www.wikidata.org/wiki/Q1522579","display_name":"Substitution (logic)","level":2,"score":0.5851395726203918},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5830626487731934},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5820456743240356},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5714085698127747},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.5426607131958008},{"id":"https://openalex.org/C2994427434","wikidata":"https://www.wikidata.org/wiki/Q35874","display_name":"Sense of humor","level":2,"score":0.4814707338809967},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4806705415248871},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12012919783592224},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1103992760181427},{"id":"https://openalex.org/C157659113","wikidata":"https://www.wikidata.org/wiki/Q533822","display_name":"WordNet","level":2,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2022.acl-long.325","doi":"https://doi.org/10.18653/v1/2022.acl-long.325","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.acl-long.325","pdf_url":"https://aclanthology.org/2022.acl-long.325.pdf","source":{"id":"https://openalex.org/S4363608652","display_name":"Annual Meeting of the Association for Computational Linguistics (ACL)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2110.07681","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2110.07681","pdf_url":"https://arxiv.org/pdf/2110.07681","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.2110.07681","doi":"https://doi.org/10.48550/arxiv.2110.07681","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2110.07681","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":"doi:10.18653/v1/2022.acl-long.325","doi":"https://doi.org/10.18653/v1/2022.acl-long.325","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2022.acl-long.325","pdf_url":"https://aclanthology.org/2022.acl-long.325.pdf","source":{"id":"https://openalex.org/S4363608652","display_name":"Annual Meeting of the Association for Computational Linguistics (ACL)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"score":0.8299999833106995,"id":"https://metadata.un.org/sdg/4","display_name":"Quality education"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G1860656004","display_name":"Information Extraction for Everyone","funder_award_id":"802774","funder_id":"https://openalex.org/F4320338335","funder_display_name":"H2020 European Research Council"},{"id":"https://openalex.org/G434337789","display_name":null,"funder_award_id":"HORIZON2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320338335","display_name":"H2020 European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3205374543.pdf","grobid_xml":"https://content.openalex.org/works/W3205374543.grobid-xml"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W64820227","https://openalex.org/W70010159","https://openalex.org/W168564468","https://openalex.org/W1513911358","https://openalex.org/W2045208889","https://openalex.org/W2101293500","https://openalex.org/W2102153514","https://openalex.org/W2117805747","https://openalex.org/W2121678312","https://openalex.org/W2127289991","https://openalex.org/W2131681506","https://openalex.org/W2153579005","https://openalex.org/W2161669948","https://openalex.org/W2164019165","https://openalex.org/W2164973920","https://openalex.org/W2185315851","https://openalex.org/W2189518090","https://openalex.org/W2250418535","https://openalex.org/W2250539671","https://openalex.org/W2250962194","https://openalex.org/W2251537235","https://openalex.org/W2490986620","https://openalex.org/W2497040301","https://openalex.org/W2507974895","https://openalex.org/W2518587255","https://openalex.org/W2522668296","https://openalex.org/W2550186622","https://openalex.org/W2551136246","https://openalex.org/W2567035470","https://openalex.org/W2574767818","https://openalex.org/W2757601816","https://openalex.org/W2799894091","https://openalex.org/W2888282873","https://openalex.org/W2947915358","https://openalex.org/W2949254265","https://openalex.org/W2951457034","https://openalex.org/W2956105246","https://openalex.org/W2963341956","https://openalex.org/W2963606136","https://openalex.org/W2963706278","https://openalex.org/W2965105341","https://openalex.org/W2970771982","https://openalex.org/W3013895536","https://openalex.org/W3021470820","https://openalex.org/W3033811073","https://openalex.org/W3099053776","https://openalex.org/W3137177596","https://openalex.org/W4386506836","https://openalex.org/W4394639182","https://openalex.org/W6950277645"],"related_works":["https://openalex.org/W2386544544","https://openalex.org/W2953949198","https://openalex.org/W3195950251","https://openalex.org/W2251000261","https://openalex.org/W2146816430","https://openalex.org/W2293111794","https://openalex.org/W2479176469","https://openalex.org/W1776998298","https://openalex.org/W4206945240","https://openalex.org/W2250962194"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,25,32,79,105,135],"word-sense":[3],"induction":[4],"method":[5,53],"based":[6],"on":[7,45,84,99,104,138],"pre-trained":[8],"masked":[9],"language":[10],"models":[11],"(MLMs),":[12],"which":[13,27,123],"can":[14],"cheaply":[15],"scale":[16],"to":[17,31,71,119],"large":[18,21],"vocabularies":[19],"and":[20,36,60,103],"corpora.The":[22],"result":[23],"is":[24,28,40],"corpus":[26],"sense-tagged":[29,50,86],"according":[30],"corpus-derived":[33],"sense":[34,39,63,129],"inventory":[35],"where":[37],"each":[38],"associated":[41],"with":[42],"indicative":[43],"words.Evaluation":[44],"English":[46],"Wikipedia":[47],"that":[48,55],"was":[49],"using":[51,134],"our":[52],"shows":[54],"both":[56],"the":[57,61,85,100,116,139],"induced":[58],"senses,":[59,122],"per-instance":[62],"assignment,":[64],"are":[65],"of":[66,115],"high":[67],"quality":[68],"even":[69],"compared":[70],"WSD":[72],"methods,":[73],"such":[74],"as":[75,131],"Babelfy.Furthermore,":[76],"by":[77],"training":[78],"static":[80,91],"word":[81],"embeddings":[82,97],"algorithm":[83,117],"corpus,":[87],"we":[88,110,132],"obtain":[89],"high-quality":[90],"senseful":[92,96],"embeddings.These":[93],"outperform":[94],"existing":[95],"methods":[98],"WiC":[101],"dataset":[102,109],"new":[106],"outlier":[107],"detection":[108],"developed.The":[111],"data":[112],"driven":[113],"nature":[114],"allows":[118],"induce":[120],"corpora-specific":[121],"may":[124],"not":[125],"appear":[126],"in":[127],"standard":[128],"inventories,":[130],"demonstrate":[133],"case":[136],"study":[137],"scientific":[140],"domain.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2025-10-10T00:00:00"}