{"id":"https://openalex.org/W2091812280","doi":"https://doi.org/10.1145/1273496.1273577","title":"Three new graphical models for statistical language modelling","display_name":"Three new graphical models for statistical language modelling","publication_year":2007,"publication_date":"2007-06-20","ids":{"openalex":"https://openalex.org/W2091812280","doi":"https://doi.org/10.1145/1273496.1273577","mag":"2091812280"},"language":"en","primary_location":{"id":"doi:10.1145/1273496.1273577","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1273496.1273577","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th international conference on Machine learning","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/A5079370148","display_name":"Andriy Mnih","orcid":null},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Andriy Mnih","raw_affiliation_strings":["University of Toronto, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108093963","display_name":"Geoffrey E. Hinton","orcid":null},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Geoffrey Hinton","raw_affiliation_strings":["University of Toronto, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.7504,"has_fulltext":false,"cited_by_count":582,"citation_normalized_percentile":{"value":0.97115585,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"641","last_page":"648"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9998000264167786,"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":0.9994999766349792,"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":0.8123974204063416},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6877889037132263},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.65777587890625},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.652259349822998},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6386878490447998},{"id":"https://openalex.org/keywords/n-gram","display_name":"n-gram","score":0.6233199834823608},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.6075074076652527},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5730095505714417},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.5680863857269287},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.557369589805603},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5199036002159119},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.48095622658729553},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.45260611176490784},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.43390417098999023},{"id":"https://openalex.org/keywords/probability-distribution","display_name":"Probability distribution","score":0.4304157495498657},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13088807463645935},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13031437993049622}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8123974204063416},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6877889037132263},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.65777587890625},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.652259349822998},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6386878490447998},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.6233199834823608},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.6075074076652527},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5730095505714417},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5680863857269287},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.557369589805603},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5199036002159119},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.48095622658729553},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.45260611176490784},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.43390417098999023},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.4304157495498657},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13088807463645935},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13031437993049622},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1145/1273496.1273577","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1273496.1273577","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th international conference on Machine learning","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.149.7757","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.149.7757","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.toronto.edu/~hinton/absps/threenew.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.304.1650","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.304.1650","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.toronto.edu/%7Eamnih/papers/threenew.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.79.11","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.79.11","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://imls.engr.oregonstate.edu/www/htdocs/proceedings/icml2007/papers/425.pdf","raw_type":"text"},{"id":"pmh:oai:eprints.ucl.ac.uk.OAI2:63252","is_oa":false,"landing_page_url":"http://discovery.ucl.ac.uk/63252/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400024","display_name":"UCL Discovery (University College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45129253","host_organization_name":"University College London","host_organization_lineage":["https://openalex.org/I45129253"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"     In: Ghahramani, Z, (ed.)   (pp. pp. 641-648).  ACM (2007)     ","raw_type":"Proceedings paper"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5600000023841858}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W10097614","https://openalex.org/W36903255","https://openalex.org/W145476170","https://openalex.org/W1558797106","https://openalex.org/W1631260214","https://openalex.org/W1808032177","https://openalex.org/W2097927681","https://openalex.org/W2116064496","https://openalex.org/W2136922672","https://openalex.org/W2147010501","https://openalex.org/W2158195707","https://openalex.org/W2160576670","https://openalex.org/W2437096199","https://openalex.org/W2998704965","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2250909759","https://openalex.org/W2532616038","https://openalex.org/W2624072012","https://openalex.org/W2787311093","https://openalex.org/W2057384730","https://openalex.org/W4307474317","https://openalex.org/W2008468404","https://openalex.org/W2147879411","https://openalex.org/W2132221452","https://openalex.org/W2081295016"],"abstract_inverted_index":{"The":[0],"supremacy":[1],"of":[2,39,54,77,90,104,122],"n-gram":[3,130],"models":[4,15,34,124],"in":[5,43],"statistical":[6],"language":[7,33],"modelling":[8],"has":[9],"recently":[10],"been":[11],"challenged":[12],"by":[13,25,50],"parametric":[14],"that":[16,35,82],"use":[17],"distributed":[18,52,61,88,96,119],"representations":[19,53,62],"to":[20,85],"counteract":[21],"the":[22,37,40,69,87,91,101,105,117,127],"difficulties":[23],"caused":[24],"data":[26],"sparsity.":[27],"We":[28,57],"propose":[29],"three":[30],"new":[31],"probabilistic":[32],"define":[36],"distribution":[38],"next":[41,92],"word":[42,93],"a":[44,74],"sequence":[45],"given":[46],"several":[47],"preceding":[48],"words":[49,64],"using":[51],"those":[55],"words.":[56],"show":[58],"how":[59],"real-valued":[60,118],"for":[63],"can":[65],"be":[66],"learned":[67],"at":[68],"same":[70],"time":[71],"as":[72,111],"learning":[73],"large":[75],"set":[76],"stochastic":[78],"binary":[79,106],"hidden":[80,107],"features":[81,108],"are":[83],"used":[84],"predict":[86],"representation":[89],"from":[94,100],"previous":[95,102],"representations.":[97,120],"Adding":[98],"connections":[99,115],"states":[103],"improves":[109],"performance":[110],"does":[112],"adding":[113],"direct":[114],"between":[116],"One":[121],"our":[123],"significantly":[125],"outperforms":[126],"very":[128],"best":[129],"models.":[131]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":22},{"year":2020,"cited_by_count":35},{"year":2019,"cited_by_count":52},{"year":2018,"cited_by_count":54},{"year":2017,"cited_by_count":65},{"year":2016,"cited_by_count":84},{"year":2015,"cited_by_count":88},{"year":2014,"cited_by_count":72},{"year":2013,"cited_by_count":22},{"year":2012,"cited_by_count":18}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}