{"id":"https://openalex.org/W2144100511","doi":"https://doi.org/10.1145/1553374.1553515","title":"Evaluation methods for topic models","display_name":"Evaluation methods for topic models","publication_year":2009,"publication_date":"2009-06-14","ids":{"openalex":"https://openalex.org/W2144100511","doi":"https://doi.org/10.1145/1553374.1553515","mag":"2144100511"},"language":"en","primary_location":{"id":"doi:10.1145/1553374.1553515","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1553374.1553515","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th Annual International Conference on Machine Learning","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.pure.ed.ac.uk/ws/files/11875992/p1105_wallach.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046348432","display_name":"Hanna Wallach","orcid":"https://orcid.org/0000-0003-3395-7186"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hanna M. Wallach","raw_affiliation_strings":["University of Massachusetts, Amherst, MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts, Amherst, MA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106707885","display_name":"Iain Murray","orcid":"https://orcid.org/0000-0002-6506-0472"},"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":"Iain Murray","raw_affiliation_strings":["University of Toronto, Toronto, Ontario, Canada","* University of Toronto, Toronto, Ontario, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Toronto, Toronto, Ontario, Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"* University of Toronto, Toronto, Ontario, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071983998","display_name":"Ruslan Salakhutdinov","orcid":"https://orcid.org/0000-0002-3752-2756"},"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":"Ruslan Salakhutdinov","raw_affiliation_strings":["University of Toronto, Toronto, Ontario, Canada","* University of Toronto, Toronto, Ontario, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Toronto, Toronto, Ontario, Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"* University of Toronto, Toronto, Ontario, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086934220","display_name":"David Mimno","orcid":"https://orcid.org/0000-0001-7510-9404"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Mimno","raw_affiliation_strings":["University of Massachusetts, Amherst, MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts, Amherst, MA","institution_ids":["https://openalex.org/I24603500"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":40.7683,"has_fulltext":true,"cited_by_count":880,"citation_normalized_percentile":{"value":0.99855758,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1105","last_page":"1112"},"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":0.9984999895095825,"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":0.9897000193595886,"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":0.7515779733657837},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.6473193764686584},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6034928560256958},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.4625270962715149},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4550245404243469},{"id":"https://openalex.org/keywords/probability-model","display_name":"Probability model","score":0.45387402176856995},{"id":"https://openalex.org/keywords/empirical-probability","display_name":"Empirical probability","score":0.4490625262260437},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4292791485786438},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3895055055618286},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.34148019552230835},{"id":"https://openalex.org/keywords/posterior-probability","display_name":"Posterior probability","score":0.3395084738731384},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.33815547823905945},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.26198941469192505},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19907021522521973},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.12320470809936523}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7515779733657837},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6473193764686584},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6034928560256958},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.4625270962715149},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4550245404243469},{"id":"https://openalex.org/C2984179964","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Probability model","level":2,"score":0.45387402176856995},{"id":"https://openalex.org/C97933134","wikidata":"https://www.wikidata.org/wiki/Q5374249","display_name":"Empirical probability","level":4,"score":0.4490625262260437},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4292791485786438},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3895055055618286},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34148019552230835},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.3395084738731384},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33815547823905945},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.26198941469192505},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19907021522521973},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.12320470809936523},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":9,"locations":[{"id":"doi:10.1145/1553374.1553515","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1553374.1553515","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th Annual International Conference on Machine Learning","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:publications/b6af6b5b-61cb-4314-8cea-10eae25216e0","is_oa":true,"landing_page_url":"http://dl.acm.org/citation.cfm?doid=1553374.1553515","pdf_url":"https://www.pure.ed.ac.uk/ws/files/11875992/p1105_wallach.pdf","source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:pure.ed.ac.uk:publications/b6af6b5b-61cb-4314-8cea-10eae25216e0","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/b6af6b5b-61cb-4314-8cea-10eae25216e0","pdf_url":"https://www.pure.ed.ac.uk/ws/files/11875992/p1105_wallach.pdf","source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Wallach, H M, Murray, I, Salakhutdinov, R & Mimno, D 2009, Evaluation methods for topic models. in Proceedings of the 26th Annual International Conference on Machine Learning (ICML '09). New York, NY, USA, pp. 1105-1112. https://doi.org/10.1145/1553374.1553515","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.149.771","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.149.771","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.umass.edu/~wallach/publications/wallach09evaluation.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.149.8078","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.149.8078","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/~murray/pub/09etm/etm.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.161.4079","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.161.4079","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/~rsalakhu/papers/etm.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.208.490","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.208.490","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://homepages.inf.ed.ac.uk/imurray2/pub/09etm/etm.pdf","raw_type":"text"},{"id":"pmh:oai:era.ed.ac.uk:1842/4587","is_oa":false,"landing_page_url":"http://hdl.handle.net/1842/4587","pdf_url":null,"source":{"id":"https://openalex.org/S7407055182","display_name":"ERA","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Conference Paper"},{"id":"pmh:oai:works.bepress.com:hanna_wallach-1014","is_oa":false,"landing_page_url":"https://works.bepress.com/hanna_wallach/8","pdf_url":null,"source":{"id":"https://openalex.org/S4306402240","display_name":"ScholarWorks@UMassAmherst (University of Massachusetts Amherst)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I24603500","host_organization_name":"University of Massachusetts Amherst","host_organization_lineage":["https://openalex.org/I24603500"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Hanna M. Wallach","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:publications/b6af6b5b-61cb-4314-8cea-10eae25216e0","is_oa":true,"landing_page_url":"http://dl.acm.org/citation.cfm?doid=1553374.1553515","pdf_url":"https://www.pure.ed.ac.uk/ws/files/11875992/p1105_wallach.pdf","source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2741668718","display_name":null,"funder_award_id":"IIS-0326249","funder_id":"https://openalex.org/F4320337389","funder_display_name":"Division of Information and Intelligent Systems"},{"id":"https://openalex.org/G7704502625","display_name":"ITR:     Unified Graphical Models of Information Extraction and Data Mining with Application to Social Network Analysis","funder_award_id":"0326249","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337389","display_name":"Division of Information and Intelligent Systems","ror":"https://ror.org/053a2cp42"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2144100511.pdf","grobid_xml":"https://content.openalex.org/works/W2144100511.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W1513873506","https://openalex.org/W1638753340","https://openalex.org/W1866610834","https://openalex.org/W1880262756","https://openalex.org/W2001082470","https://openalex.org/W2015749074","https://openalex.org/W2104210067","https://openalex.org/W2106490775","https://openalex.org/W2112971401","https://openalex.org/W2140124448","https://openalex.org/W2147357149","https://openalex.org/W2157002241","https://openalex.org/W2158266063","https://openalex.org/W2172135926","https://openalex.org/W2912651257","https://openalex.org/W6676893574","https://openalex.org/W6680343917"],"related_works":["https://openalex.org/W2320870285","https://openalex.org/W2354548288","https://openalex.org/W2347896881","https://openalex.org/W1968823131","https://openalex.org/W1729726137","https://openalex.org/W2138266733","https://openalex.org/W4236175165","https://openalex.org/W2083453346","https://openalex.org/W1976498654","https://openalex.org/W2358572162"],"abstract_inverted_index":{"A":[0],"natural":[1],"evaluation":[2],"metric":[3],"for":[4,28],"statistical":[5],"topic":[6,36],"models":[7],"is":[8,24],"the":[9,35,40,62],"probability":[10,23,30,63],"of":[11,21,64],"held-out":[12],"documents":[13],"given":[14],"a":[15],"trained":[16],"model.":[17],"While":[18],"exact":[19],"computation":[20],"this":[22,29,49],"intractable,":[25],"several":[26],"estimators":[27],"have":[31],"been":[32],"used":[33],"in":[34],"modeling":[37],"literature,":[38],"including":[39],"harmonic":[41],"mean":[42],"method":[43],"and":[44,67,76],"empirical":[45],"likelihood":[46],"method.":[47],"In":[48],"paper,":[50],"we":[51],"demonstrate":[52],"experimentally":[53],"that":[54,72],"commonly-used":[55],"methods":[56,71],"are":[57,73],"unlikely":[58],"to":[59],"accurately":[60],"estimate":[61],"heldout":[65],"documents,":[66],"propose":[68],"two":[69],"alternative":[70],"both":[74],"accurate":[75],"efficient.":[77],"1.":[78]},"counts_by_year":[{"year":2026,"cited_by_count":15},{"year":2025,"cited_by_count":39},{"year":2024,"cited_by_count":37},{"year":2023,"cited_by_count":58},{"year":2022,"cited_by_count":47},{"year":2021,"cited_by_count":86},{"year":2020,"cited_by_count":61},{"year":2019,"cited_by_count":66},{"year":2018,"cited_by_count":70},{"year":2017,"cited_by_count":62},{"year":2016,"cited_by_count":79},{"year":2015,"cited_by_count":66},{"year":2014,"cited_by_count":63},{"year":2013,"cited_by_count":40},{"year":2012,"cited_by_count":39}],"updated_date":"2026-06-18T10:00:31.954636","created_date":"2025-10-10T00:00:00"}