{"id":"https://openalex.org/W2158085718","doi":"https://doi.org/10.1145/1553374.1553378","title":"Incorporating domain knowledge into topic modeling via Dirichlet Forest priors","display_name":"Incorporating domain knowledge into topic modeling via Dirichlet Forest priors","publication_year":2009,"publication_date":"2009-06-14","ids":{"openalex":"https://openalex.org/W2158085718","doi":"https://doi.org/10.1145/1553374.1553378","mag":"2158085718","pmid":"https://pubmed.ncbi.nlm.nih.gov/20871805"},"language":"en","primary_location":{"id":"doi:10.1145/1553374.1553378","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1553374.1553378","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","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051840175","display_name":"David Andrzejewski","orcid":null},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"David Andrzejewski","raw_affiliation_strings":["University of Wisconsin-Madison, Madison, WI"],"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison, Madison, WI","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103428074","display_name":"Xiaojin Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaojin Zhu","raw_affiliation_strings":["University of Wisconsin-Madison, Madison, WI"],"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison, Madison, WI","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071722704","display_name":"Mark Craven","orcid":"https://orcid.org/0000-0002-8917-7464"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Craven","raw_affiliation_strings":["University of Wisconsin-Madison, Madison, WI"],"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison, Madison, WI","institution_ids":["https://openalex.org/I135310074"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5051840175"],"corresponding_institution_ids":["https://openalex.org/I135310074"],"apc_list":null,"apc_paid":null,"fwci":22.5814,"has_fulltext":false,"cited_by_count":430,"citation_normalized_percentile":{"value":0.99570878,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"382","issue":"26","first_page":"25","last_page":"32"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9997000098228455,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9890000224113464,"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/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.8443955183029175},{"id":"https://openalex.org/keywords/dirichlet-distribution","display_name":"Dirichlet distribution","score":0.8102459907531738},{"id":"https://openalex.org/keywords/gibbs-sampling","display_name":"Gibbs sampling","score":0.7648974657058716},{"id":"https://openalex.org/keywords/hierarchical-dirichlet-process","display_name":"Hierarchical Dirichlet process","score":0.7136706113815308},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.7024668455123901},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.692497968673706},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6708738803863525},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.630964994430542},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5270172357559204},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45823246240615845},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4089524745941162},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.363740473985672},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.25253811478614807},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.11142328381538391}],"concepts":[{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.8443955183029175},{"id":"https://openalex.org/C169214877","wikidata":"https://www.wikidata.org/wiki/Q981016","display_name":"Dirichlet distribution","level":3,"score":0.8102459907531738},{"id":"https://openalex.org/C158424031","wikidata":"https://www.wikidata.org/wiki/Q1191905","display_name":"Gibbs sampling","level":3,"score":0.7648974657058716},{"id":"https://openalex.org/C141318989","wikidata":"https://www.wikidata.org/wiki/Q5753066","display_name":"Hierarchical Dirichlet process","level":4,"score":0.7136706113815308},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.7024668455123901},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.692497968673706},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6708738803863525},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.630964994430542},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5270172357559204},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45823246240615845},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4089524745941162},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.363740473985672},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25253811478614807},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.11142328381538391},{"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/C182310444","wikidata":"https://www.wikidata.org/wiki/Q1332643","display_name":"Boundary value problem","level":2,"score":0.0}],"mesh":[],"locations_count":8,"locations":[{"id":"doi:10.1145/1553374.1553378","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1553374.1553378","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":"pmid:20871805","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/20871805","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ... International Conference on Machine Learning. International Conference on Machine Learning","raw_type":null},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.149.7647","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.149.7647","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.mcgill.ca/~icml2009/papers/390.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.153.3465","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.153.3465","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cs.wisc.edu/~jerryzhu/pub/itopic.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.216.9551","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.216.9551","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.biostat.wisc.edu/~craven/papers/andr-icml09.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.309.8140","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.309.8140","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://pages.cs.wisc.edu/~andrzeje/publications/icml-2009.pdf","raw_type":"text"},{"id":"pmh:oai:pubmedcentral.nih.gov:2943854","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proc Int Conf Mach Learn","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:2943854","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/2943854","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proc Int Conf Mach Learn","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:2943854","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proc Int Conf Mach Learn","raw_type":"Text"},"sustainable_development_goals":[{"score":0.6899999976158142,"id":"https://metadata.un.org/sdg/15","display_name":"Life in Land"}],"awards":[{"id":"https://openalex.org/G2426079815","display_name":null,"funder_award_id":"T15 LM07359R01 LM07050","funder_id":"https://openalex.org/F4320337372","funder_display_name":"U.S. National Library of Medicine"}],"funders":[{"id":"https://openalex.org/F4320337372","display_name":"U.S. National Library of Medicine","ror":"https://ror.org/0060t0j89"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1516407653","https://openalex.org/W1880262756","https://openalex.org/W2001082470","https://openalex.org/W2026899404","https://openalex.org/W2070147577","https://openalex.org/W2096610504","https://openalex.org/W2103017472","https://openalex.org/W2106490775","https://openalex.org/W2112050062","https://openalex.org/W2134678128","https://openalex.org/W2153662225","https://openalex.org/W2157522502","https://openalex.org/W2912651257","https://openalex.org/W2990138404"],"related_works":["https://openalex.org/W2939843948","https://openalex.org/W2891616219","https://openalex.org/W2097627380","https://openalex.org/W2914864478","https://openalex.org/W2008338582","https://openalex.org/W4291700620","https://openalex.org/W1999586157","https://openalex.org/W22044811","https://openalex.org/W2625329765","https://openalex.org/W2352674739"],"abstract_inverted_index":{"Users":[0],"of":[1,11,45],"topic":[2],"modeling":[3],"methods":[4],"often":[5],"have":[6,15],"knowledge":[7,27],"about":[8],"the":[9],"composition":[10],"words":[12],"that":[13],"should":[14],"high":[16],"or":[17],"low":[18],"probability":[19],"in":[20,34],"various":[21],"topics.":[22],"We":[23,52],"incorporate":[24],"such":[25],"domain":[26,78],"using":[28],"a":[29,35,43],"novel":[30],"Dirichlet":[31,37,46],"Forest":[32],"prior":[33,41],"Latent":[36],"Allocation":[38],"framework.":[39],"The":[40],"is":[42],"mixture":[44],"tree":[47],"distributions":[48],"with":[49],"special":[50],"structures.":[51],"present":[53],"its":[54],"construction,":[55],"and":[56,65,74],"inference":[57],"via":[58],"collapsed":[59],"Gibbs":[60],"sampling.":[61],"Experiments":[62],"on":[63],"synthetic":[64],"real":[66],"datasets":[67],"demonstrate":[68],"our":[69],"model's":[70],"ability":[71],"to":[72],"follow":[73],"generalize":[75],"beyond":[76],"user-specified":[77],"knowledge.":[79]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":20},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":40},{"year":2019,"cited_by_count":38},{"year":2018,"cited_by_count":40},{"year":2017,"cited_by_count":43},{"year":2016,"cited_by_count":48},{"year":2015,"cited_by_count":58},{"year":2014,"cited_by_count":30},{"year":2013,"cited_by_count":19},{"year":2012,"cited_by_count":23}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}