{"id":"https://openalex.org/W1986966428","doi":"https://doi.org/10.1145/1008992.1009016","title":"GaP","display_name":"GaP","publication_year":2004,"publication_date":"2004-07-25","ids":{"openalex":"https://openalex.org/W1986966428","doi":"https://doi.org/10.1145/1008992.1009016","mag":"1986966428"},"language":"en","primary_location":{"id":"doi:10.1145/1008992.1009016","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1008992.1009016","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089723214","display_name":"John Canny","orcid":"https://orcid.org/0000-0002-7161-7927"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"John Canny","raw_affiliation_strings":["University of California, Berkeley, CA","University of California: Berkeley, CA#TAB#"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, CA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California: Berkeley, CA#TAB#","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5089723214"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":13.4134,"has_fulltext":false,"cited_by_count":178,"citation_normalized_percentile":{"value":0.98700466,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"122","last_page":"129"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9980000257492065,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9980000257492065,"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":0.9973999857902527,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9970999956130981,"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/perplexity","display_name":"Perplexity","score":0.7950886487960815},{"id":"https://openalex.org/keywords/factorization","display_name":"Factorization","score":0.6004830598831177},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5761234760284424},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5061370730400085},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.46147677302360535},{"id":"https://openalex.org/keywords/random-variable","display_name":"Random variable","score":0.45785626769065857},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.4425562620162964},{"id":"https://openalex.org/keywords/poisson-distribution","display_name":"Poisson distribution","score":0.44085124135017395},{"id":"https://openalex.org/keywords/independence","display_name":"Independence (probability theory)","score":0.42602238059043884},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3807187080383301},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3781939744949341},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.2980315089225769},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2816826403141022},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.20299822092056274},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.12108767032623291}],"concepts":[{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.7950886487960815},{"id":"https://openalex.org/C187834632","wikidata":"https://www.wikidata.org/wiki/Q188804","display_name":"Factorization","level":2,"score":0.6004830598831177},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5761234760284424},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5061370730400085},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.46147677302360535},{"id":"https://openalex.org/C122123141","wikidata":"https://www.wikidata.org/wiki/Q176623","display_name":"Random variable","level":2,"score":0.45785626769065857},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.4425562620162964},{"id":"https://openalex.org/C100906024","wikidata":"https://www.wikidata.org/wiki/Q205692","display_name":"Poisson distribution","level":2,"score":0.44085124135017395},{"id":"https://openalex.org/C35651441","wikidata":"https://www.wikidata.org/wiki/Q625303","display_name":"Independence (probability theory)","level":2,"score":0.42602238059043884},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3807187080383301},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3781939744949341},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2980315089225769},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2816826403141022},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.20299822092056274},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.12108767032623291}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1008992.1009016","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1008992.1009016","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1880262756","https://openalex.org/W1983578042","https://openalex.org/W2013029404","https://openalex.org/W2095764546","https://openalex.org/W2107743791","https://openalex.org/W2123649031","https://openalex.org/W2135029798","https://openalex.org/W2136542423","https://openalex.org/W2141224535","https://openalex.org/W2158997610","https://openalex.org/W3143596294","https://openalex.org/W4233135949","https://openalex.org/W4240913316"],"related_works":["https://openalex.org/W2376415519","https://openalex.org/W4294769427","https://openalex.org/W1895908943","https://openalex.org/W4225667838","https://openalex.org/W1601381279","https://openalex.org/W4281893144","https://openalex.org/W2374747083","https://openalex.org/W2293120661","https://openalex.org/W2170667735","https://openalex.org/W2096126648"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,6,37,52,67,78,92,137,145,156],"probabilistic":[3,69,138],"model":[4,20,70,123,139,150],"for":[5,24],"document":[7,116],"corpus":[8],"that":[9,40,71],"combines":[10],"many":[11],"of":[12,16,28,47,54,95,120,159,166],"the":[13,26,29,48,97,103,121,169],"desirable":[14],"features":[15],"previous":[17],"models.":[18],"The":[19,118,148],"is":[21,36,41,66,124],"called":[22],"\"GaP\"":[23],"Gamma-Poisson,":[25],"distributions":[27],"first":[30],"and":[31,57,87,143,153,161],"last":[32],"random":[33],"variable.":[34],"GaP":[35,65,98,122,149],"factor":[38],"model,":[39],"it":[42,106],"gives":[43,132],"an":[44,85,111],"approximate":[45],"factorization":[46,99],"document-term":[49],"matrix":[50],"into":[51,155],"product":[53],"matrices":[55],"\u039b":[56],"X.":[58],"These":[59],"factors":[60],"have":[61],"strictly":[62],"non-negative":[63],"terms.":[64],"generative":[68],"assigns":[72],"finite":[73],"probabilities":[74],"to":[75,115],"documents":[76,152],"in":[77],"corpus.":[79],"It":[80,131],"can":[81,107],"be":[82,108],"computed":[83],"with":[84],"efficient":[86],"simple":[88],"EM":[89],"recurrence.":[90],"For":[91],"suitable":[93],"choice":[94],"parameters,":[96],"maximizes":[100],"independence":[101],"between":[102],"factors.":[104],"So":[105],"used":[109],"as":[110,126,128,136,144,164],"independent-component":[112],"algorithm":[113],"adapted":[114],"data.":[117],"form":[119],"empirically":[125],"well":[127],"analytically":[129],"motivated.":[130],"very":[133],"accurate":[134],"results":[135],"(measured":[140],"via":[141],"perplexity)":[142],"retrieval":[146],"model.":[147],"projects":[151],"terms":[154,167],"low-dimensional":[157],"space":[158],"\"themes,\"":[160],"models":[162],"texts":[163],"\"passages\"":[165],"on":[168],"same":[170],"theme.":[171]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":17},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":17},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":14},{"year":2015,"cited_by_count":17},{"year":2014,"cited_by_count":14},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":11}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2016-06-24T00:00:00"}