{"id":"https://openalex.org/W2123092185","doi":"https://doi.org/10.3115/1034678.1034694","title":"Distributional similarity models","display_name":"Distributional similarity models","publication_year":1999,"publication_date":"1999-01-01","ids":{"openalex":"https://openalex.org/W2123092185","doi":"https://doi.org/10.3115/1034678.1034694","mag":"2123092185"},"language":"en","primary_location":{"id":"doi:10.3115/1034678.1034694","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1034678.1034694","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1034678.1034694","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th annual meeting of the Association for Computational Linguistics on Computational Linguistics  -","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.3115/1034678.1034694","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076876084","display_name":"Lillian Lee","orcid":"https://orcid.org/0000-0003-4770-1712"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Lillian Lee","raw_affiliation_strings":["Cornell University, Ithaca, NY"],"affiliations":[{"raw_affiliation_string":"Cornell University, Ithaca, NY","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044708805","display_name":"Fernando Pereira","orcid":"https://orcid.org/0000-0001-6100-947X"},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fernando Pereira","raw_affiliation_strings":["A247, AT&T Labs - Research, Florham Park, NJ"],"affiliations":[{"raw_affiliation_string":"A247, AT&T Labs - Research, Florham Park, NJ","institution_ids":["https://openalex.org/I1283103587"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5076876084"],"corresponding_institution_ids":["https://openalex.org/I205783295"],"apc_list":null,"apc_paid":null,"fwci":5.0976,"has_fulltext":true,"cited_by_count":31,"citation_normalized_percentile":{"value":0.95356972,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"33","last_page":"40"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.991100013256073,"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":0.991100013256073,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.987500011920929,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9708999991416931,"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/similarity","display_name":"Similarity (geometry)","score":0.7407090067863464},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6235004663467407},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5992114543914795},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.5315535068511963},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4420022666454315},{"id":"https://openalex.org/keywords/rare-events","display_name":"Rare events","score":0.4114089906215668},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.410597026348114},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.29635608196258545},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.28412580490112305}],"concepts":[{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.7407090067863464},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6235004663467407},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5992114543914795},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.5315535068511963},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4420022666454315},{"id":"https://openalex.org/C2777317252","wikidata":"https://www.wikidata.org/wiki/Q18393516","display_name":"Rare events","level":2,"score":0.4114089906215668},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.410597026348114},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.29635608196258545},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.28412580490112305},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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":1,"locations":[{"id":"doi:10.3115/1034678.1034694","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1034678.1034694","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1034678.1034694","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th annual meeting of the Association for Computational Linguistics on Computational Linguistics  -","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.3115/1034678.1034694","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1034678.1034694","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1034678.1034694","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th annual meeting of the Association for Computational Linguistics on Computational Linguistics  -","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","score":0.4300000071525574,"display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2123092185.pdf","grobid_xml":"https://content.openalex.org/works/W2123092185.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W161643443","https://openalex.org/W1593239840","https://openalex.org/W1597533204","https://openalex.org/W1731244441","https://openalex.org/W2016001305","https://openalex.org/W2035967403","https://openalex.org/W2059800182","https://openalex.org/W2064580901","https://openalex.org/W2106231890","https://openalex.org/W2120084270","https://openalex.org/W2121227244","https://openalex.org/W2127314673","https://openalex.org/W2134237567","https://openalex.org/W2143144851","https://openalex.org/W2146950091","https://openalex.org/W2278264611","https://openalex.org/W2295097532","https://openalex.org/W2949791182"],"related_works":["https://openalex.org/W1619455259","https://openalex.org/W4388734940","https://openalex.org/W2375480909","https://openalex.org/W2353314428","https://openalex.org/W4381616548","https://openalex.org/W2012019886","https://openalex.org/W2166090428","https://openalex.org/W2381021552","https://openalex.org/W2354749003","https://openalex.org/W2969346978"],"abstract_inverted_index":{"Distributional":[0],"similarity":[1],"is":[2],"a":[3,37],"useful":[4],"notion":[5],"in":[6],"estimating":[7],"the":[8,43],"probabilities":[9],"of":[10,31,36,58],"rare":[11],"joint":[12],"events.":[13,60],"It":[14],"has":[15],"been":[16],"employed":[17],"both":[18],"to":[19,23,27],"cluster":[20],"events":[21],"according":[22],"their":[24],"distributions,":[25],"and":[26,48,53],"directly":[28],"compute":[29],"averages":[30],"estimates":[32],"for":[33,51],"distributional":[34,56],"neighbors":[35,55],"target":[38],"event.":[39],"Here,":[40],"we":[41],"examine":[42],"tradeoffs":[44],"between":[45],"model":[46],"size":[47],"prediction":[49],"accuracy":[50],"cluster-based":[52],"nearest":[54],"models":[57],"unseen":[59]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}