{"id":"https://openalex.org/W2053354515","doi":"https://doi.org/10.1145/2187836.2187936","title":"Document hierarchies from text and links","display_name":"Document hierarchies from text and links","publication_year":2012,"publication_date":"2012-04-16","ids":{"openalex":"https://openalex.org/W2053354515","doi":"https://doi.org/10.1145/2187836.2187936","mag":"2053354515"},"language":"en","primary_location":{"id":"doi:10.1145/2187836.2187936","doi":"https://doi.org/10.1145/2187836.2187936","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2187836.2187936","pdf_url":null,"source":{"id":"https://openalex.org/S7407088480","display_name":"International World Wide Web Conference (WWW)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st international conference on World Wide Web","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","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/A5012361506","display_name":"Qirong Ho","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qirong Ho","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA","Carnegie-Mellon University, Pittsburgh, Pa., USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie-Mellon University, Pittsburgh, Pa., USA#TAB#","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047699861","display_name":"Jacob Eisenstein","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jacob Eisenstein","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009547049","display_name":"Eric P. Xing","orcid":"https://orcid.org/0009-0005-9158-4201","observed_orcids":["https://orcid.org/0009-0005-9158-4201","https://orcid.org/0000-0002-3683-4280"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric P. Xing","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA","Carnegie-Mellon University, Pittsburgh, Pa., USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie-Mellon University, Pittsburgh, Pa., USA#TAB#","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.4838,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.95936404,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"739","last_page":"748"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.6640999913215637,"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":0.6640999913215637,"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/T10064","display_name":"Complex Network Analysis Techniques","score":0.11320000141859055,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.052000001072883606,"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/hierarchical-document-structure","display_name":"hierarchical document structure","score":0.8019999861717224},{"id":"https://openalex.org/keywords/hierarchical-taxonomy","display_name":"hierarchical taxonomy","score":0.8920000195503235},{"id":"https://openalex.org/keywords/bayesian-generative-models","display_name":"Bayesian generative models","score":0.7860000133514404},{"id":"https://openalex.org/keywords/nonparametric-bayesian-models","display_name":"nonparametric Bayesian models","score":0.9480000138282776},{"id":"https://openalex.org/keywords/network-structure","display_name":"network structure","score":0.6880000233650208},{"id":"https://openalex.org/keywords/citation-networks","display_name":"citation networks","score":0.9869999885559082}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8324666023254395},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5156189799308777},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.5142945647239685},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.5070559978485107},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.4829806387424469},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4283648729324341},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4189559817314148},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.41705816984176636},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4042327404022217},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2790147364139557}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/2187836.2187936","doi":"https://doi.org/10.1145/2187836.2187936","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2187836.2187936","pdf_url":null,"source":{"id":"https://openalex.org/S7407088480","display_name":"International World Wide Web Conference (WWW)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st international conference on World Wide Web","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.220.2030","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.220.2030","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cmu.edu/%7Eepxing/papers/2012/Ho_Eisenstein_Xing_WWW12.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.232.5132","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.232.5132","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www2012.wwwconference.org/proceedings/proceedings/p739.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.650.8321","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.650.8321","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cc.gatech.edu/~jeisenst/papers/www2012.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320337398","display_name":"Division of Biological Infrastructure","ror":"https://ror.org/04qn9mx93"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W75368837","https://openalex.org/W130710483","https://openalex.org/W146900863","https://openalex.org/W1482549160","https://openalex.org/W1532325895","https://openalex.org/W1547561528","https://openalex.org/W1682705844","https://openalex.org/W1848279521","https://openalex.org/W1985093013","https://openalex.org/W1995996823","https://openalex.org/W1996764654","https://openalex.org/W2001082470","https://openalex.org/W2039346806","https://openalex.org/W2066680326","https://openalex.org/W2102717275","https://openalex.org/W2105179799","https://openalex.org/W2107107106","https://openalex.org/W2108346334","https://openalex.org/W2114165195","https://openalex.org/W2121947440","https://openalex.org/W2124067180","https://openalex.org/W2124168655","https://openalex.org/W2124470082","https://openalex.org/W2124672527","https://openalex.org/W2128999403","https://openalex.org/W2130978632","https://openalex.org/W2138858509","https://openalex.org/W2140124448","https://openalex.org/W2145036943","https://openalex.org/W2146936057","https://openalex.org/W2150102617","https://openalex.org/W2150286230","https://openalex.org/W2150461699","https://openalex.org/W2157082398","https://openalex.org/W2158266063","https://openalex.org/W2165636119","https://openalex.org/W2166354010","https://openalex.org/W2168735666","https://openalex.org/W2171836785","https://openalex.org/W2185870924","https://openalex.org/W2251320462","https://openalex.org/W2289549408","https://openalex.org/W2334311856","https://openalex.org/W2610700150","https://openalex.org/W4241122026","https://openalex.org/W4292691288","https://openalex.org/W6637242313","https://openalex.org/W6816560326"],"related_works":["https://openalex.org/W1971883301","https://openalex.org/W4237723370","https://openalex.org/W2115620960","https://openalex.org/W2251021198","https://openalex.org/W2118722427","https://openalex.org/W3023960840","https://openalex.org/W7095679311","https://openalex.org/W7117652930","https://openalex.org/W7172004570","https://openalex.org/W4234583424"],"abstract_inverted_index":{"Hierarchical":[0],"taxonomies":[1,28],"provide":[2],"a":[3,44,50,74],"multi-level":[4],"view":[5],"of":[6,21,63,84,96,108,113,123,146],"large":[7],"document":[8],"collections,":[9],"allowing":[10],"users":[11],"to":[12,16,127],"rapidly":[13],"drill":[14],"down":[15],"fine-grained":[17],"distinctions":[18],"in":[19,48,120],"topics":[20],"interest.":[22],"We":[23],"show":[24],"that":[25],"automatically":[26],"induced":[27],"can":[29],"be":[30],"made":[31],"more":[32,130],"robust":[33],"by":[34],"combining":[35],"text":[36],"with":[37,65,129],"relational":[38],"links.":[39],"The":[40],"underlying":[41],"mechanism":[42],"is":[43],"Bayesian":[45,76],"generative":[46],"model":[47],"which":[49],"latent":[51,105],"hierarchical":[52,61],"structure":[53],"explains":[54],"the":[55,85,93,100,111,121,144],"observed":[56],"data":[57],"---":[58],"thus,":[59],"finding":[60],"groups":[62],"documents":[64],"similar":[66],"word":[67],"distributions":[68],"and":[69,139],"dense":[70],"network":[71,109,141],"connections.":[72],"As":[73],"nonparametric":[75],"model,":[77],"our":[78,114,147],"approach":[79,115],"does":[80,116],"not":[81,117],"require":[82],"pre-specification":[83],"branching":[86],"factor":[87],"at":[88],"each":[89],"non-terminal,":[90],"but":[91],"finds":[92],"appropriate":[94],"level":[95],"detail":[97],"directly":[98],"from":[99],"data.":[101],"Unlike":[102],"many":[103],"prior":[104],"space":[106],"models":[107],"structure,":[110],"complexity":[112],"grow":[118],"quadratically":[119],"number":[122],"documents,":[124],"enabling":[125],"application":[126],"networks":[128],"than":[131],"ten":[132],"thousand":[133],"nodes.":[134],"Experimental":[135],"results":[136],"on":[137],"hypertext":[138],"citation":[140],"corpora":[142],"demonstrate":[143],"advantages":[145],"hierarchical,":[148],"multimodal":[149],"approach.":[150]},"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":5},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}