{"id":"https://openalex.org/W2168488431","doi":"https://doi.org/10.1145/2232817.2232861","title":"Topic models for taxonomies","display_name":"Topic models for taxonomies","publication_year":2012,"publication_date":"2012-06-10","ids":{"openalex":"https://openalex.org/W2168488431","doi":"https://doi.org/10.1145/2232817.2232861","mag":"2168488431"},"language":"en","primary_location":{"id":"doi:10.1145/2232817.2232861","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2232817.2232861","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th ACM/IEEE-CS joint conference on Digital Libraries","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://works.bepress.com/andrew_mccallum/26","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072205226","display_name":"Anton Bakalov","orcid":null},"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":"Anton Bakalov","raw_affiliation_strings":["University of Massachusetts Amherst, Amherst, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008354502","display_name":"Andrew McCallum","orcid":"https://orcid.org/0000-0003-2843-6992"},"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":"Andrew McCallum","raw_affiliation_strings":["University of Massachusetts Amherst, Amherst, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","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 Wallach","raw_affiliation_strings":["University of Massachusetts Amherst, Amherst, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]},{"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/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Mimno","raw_affiliation_strings":["Princeton University, Princeton, NJ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University, Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.9806,"has_fulltext":true,"cited_by_count":26,"citation_normalized_percentile":{"value":0.93934056,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"237","last_page":"240"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9987999796867371,"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":0.9987999796867371,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.9961000084877014,"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/taxonomy","display_name":"Taxonomy (biology)","score":0.8446668386459351},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.835726797580719},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6566516160964966},{"id":"https://openalex.org/keywords/cataloging","display_name":"Cataloging","score":0.6158554553985596},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.5545804500579834},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4555434584617615},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45185768604278564},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41118893027305603},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3365950584411621},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.32782337069511414},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07182896137237549}],"concepts":[{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.8446668386459351},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.835726797580719},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6566516160964966},{"id":"https://openalex.org/C2777922441","wikidata":"https://www.wikidata.org/wiki/Q3535655","display_name":"Cataloging","level":2,"score":0.6158554553985596},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.5545804500579834},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4555434584617615},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45185768604278564},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41118893027305603},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3365950584411621},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.32782337069511414},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07182896137237549},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/2232817.2232861","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2232817.2232861","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th ACM/IEEE-CS joint conference on Digital Libraries","raw_type":"proceedings-article"},{"id":"pmh:oai:works.bepress.com:andrew_mccallum-1036","is_oa":true,"landing_page_url":"https://works.bepress.com/andrew_mccallum/26","pdf_url":"https://works.bepress.com/andrew_mccallum/26","source":{"id":"https://openalex.org/S4306402057","display_name":"Scholarworks (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":"Andrew McCallum","raw_type":"text"},{"id":"pmh:oai:works.bepress.com:hanna_wallach-1034","is_oa":true,"landing_page_url":"https://works.bepress.com/hanna_wallach/18","pdf_url":"https://works.bepress.com/hanna_wallach/18","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"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.259.3194","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.259.3194","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://people.cs.umass.edu/%7Eabakalov/papers/jcdl12-lpam.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:works.bepress.com:andrew_mccallum-1036","is_oa":true,"landing_page_url":"https://works.bepress.com/andrew_mccallum/26","pdf_url":"https://works.bepress.com/andrew_mccallum/26","source":{"id":"https://openalex.org/S4306402057","display_name":"Scholarworks (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":"Andrew McCallum","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2168488431.pdf","grobid_xml":"https://content.openalex.org/works/W2168488431.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W1508001288","https://openalex.org/W1880262756","https://openalex.org/W1915058860","https://openalex.org/W1969486090","https://openalex.org/W1973515220","https://openalex.org/W2122678284","https://openalex.org/W2132827946","https://openalex.org/W2135181562","https://openalex.org/W2138051266","https://openalex.org/W2140124448","https://openalex.org/W2144100511","https://openalex.org/W2289346390"],"related_works":["https://openalex.org/W2011236053","https://openalex.org/W2349695282","https://openalex.org/W2079670513","https://openalex.org/W2380481257","https://openalex.org/W2082220406","https://openalex.org/W2035691235","https://openalex.org/W2139226347","https://openalex.org/W2069391836","https://openalex.org/W4254603770","https://openalex.org/W2362822043"],"abstract_inverted_index":{"Concept":[0],"taxonomies":[1],"such":[2],"as":[3],"MeSH,":[4],"the":[5,11,48,66,98,110],"ACM":[6],"Computing":[7],"Classification":[8],"System,":[9],"and":[10,39,55,62],"NY":[12],"Times":[13],"Subject":[14],"Headings":[15],"are":[16,41],"frequently":[17],"used":[18],"to":[19,45,118],"help":[20],"organize":[21],"data.":[22],"They":[23],"typically":[24],"consist":[25],"of":[26,29,51,89],"a":[27,34,52,78,87,113],"set":[28],"concept":[30],"names":[31,38],"organized":[32],"in":[33],"hierarchy.":[35],"However,":[36],"these":[37],"structure":[40],"often":[42],"not":[43],"sufficient":[44],"fully":[46],"capture":[47],"intended":[49],"meaning":[50],"taxonomy":[53,80,102],"node,":[54],"particularly":[56],"non-experts":[57],"may":[58],"have":[59],"difficulty":[60],"navigating":[61],"placing":[63],"data":[64],"into":[65],"taxonomy.":[67],"This":[68],"paper":[69],"introduces":[70],"two":[71],"semi-supervised":[72],"topic":[73],"models":[74,111],"that":[75,95],"automatically":[76],"augment":[77],"given":[79],"with":[81],"many":[82],"additional":[83],"keywords":[84],"by":[85],"leveraging":[86],"corpus":[88],"multi-labeled":[90],"documents.":[91],"Our":[92],"experiments":[93],"show":[94],"users":[96],"find":[97],"topics":[99],"beneficial":[100],"for":[101],"interpretation,":[103],"substantially":[104],"increasing":[105],"their":[106],"cataloging":[107],"accuracy.":[108],"Furthermore,":[109],"provide":[112],"better":[114],"information":[115],"rate":[116],"compared":[117],"Labeled":[119],"LDA.":[120]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
