{"id":"https://openalex.org/W2538484347","doi":"https://doi.org/10.1145/2983323.2983810","title":"Beyond Clustering","display_name":"Beyond Clustering","publication_year":2016,"publication_date":"2016-10-24","ids":{"openalex":"https://openalex.org/W2538484347","doi":"https://doi.org/10.1145/2983323.2983810","mag":"2538484347"},"language":"en","primary_location":{"id":"doi:10.1145/2983323.2983810","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2983323.2983810","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM International on Conference on Information and Knowledge Management","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/A5063416855","display_name":"Ramakrishna Bairi","orcid":"https://orcid.org/0009-0009-9191-3748"},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Ramakrishna B. Bairi","raw_affiliation_strings":["Indian Institute of Technology,Bombay, Mumbai, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology,Bombay, Mumbai, India","institution_ids":["https://openalex.org/I162827531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069487278","display_name":"Mark Carman","orcid":"https://orcid.org/0000-0001-6575-9737"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Mark J. Carman","raw_affiliation_strings":["Monash University, Melbourne, Australia"],"affiliations":[{"raw_affiliation_string":"Monash University, Melbourne, Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089606464","display_name":"Ganesh Ramakrishnan","orcid":"https://orcid.org/0000-0003-4533-2490"},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ganesh Ramakrishnan","raw_affiliation_strings":["Indian Institute of Technology,Bombay, Mumbai, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology,Bombay, Mumbai, India","institution_ids":["https://openalex.org/I162827531"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5063416855"],"corresponding_institution_ids":["https://openalex.org/I162827531"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.06970783,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"801","last_page":"810"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9983999729156494,"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":0.9983999729156494,"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":0.9983999729156494,"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":0.9958999752998352,"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":0.7633890509605408},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6396579742431641},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.521100640296936},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.5107972621917725},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.49887895584106445},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.49122780561447144},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4865352213382721},{"id":"https://openalex.org/keywords/gibbs-sampling","display_name":"Gibbs sampling","score":0.47024407982826233},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.46851181983947754},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.45295393466949463},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43667787313461304},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.4132285714149475},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4125269055366516},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.41055017709732056},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.38121938705444336},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3607296347618103},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.30556803941726685}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7633890509605408},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6396579742431641},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.521100640296936},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.5107972621917725},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.49887895584106445},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.49122780561447144},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4865352213382721},{"id":"https://openalex.org/C158424031","wikidata":"https://www.wikidata.org/wiki/Q1191905","display_name":"Gibbs sampling","level":3,"score":0.47024407982826233},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.46851181983947754},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.45295393466949463},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43667787313461304},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.4132285714149475},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4125269055366516},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.41055017709732056},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.38121938705444336},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3607296347618103},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.30556803941726685},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2983323.2983810","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2983323.2983810","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM International on Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6399999856948853,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W55768394","https://openalex.org/W177984263","https://openalex.org/W1548663377","https://openalex.org/W1598683382","https://openalex.org/W1880262756","https://openalex.org/W1969486090","https://openalex.org/W2019599312","https://openalex.org/W2022166150","https://openalex.org/W2031046392","https://openalex.org/W2033227606","https://openalex.org/W2042980227","https://openalex.org/W2047706513","https://openalex.org/W2052684427","https://openalex.org/W2063862666","https://openalex.org/W2065843886","https://openalex.org/W2066680326","https://openalex.org/W2067292826","https://openalex.org/W2094728533","https://openalex.org/W2102150019","https://openalex.org/W2106490775","https://openalex.org/W2113855231","https://openalex.org/W2120232387","https://openalex.org/W2123142779","https://openalex.org/W2127723919","https://openalex.org/W2131357087","https://openalex.org/W2132827946","https://openalex.org/W2135140174","https://openalex.org/W2150766729","https://openalex.org/W2155440340","https://openalex.org/W2158266063","https://openalex.org/W2165232124","https://openalex.org/W2169463693","https://openalex.org/W2251656679","https://openalex.org/W2334889010","https://openalex.org/W2699188281","https://openalex.org/W2789478670","https://openalex.org/W2897438987","https://openalex.org/W6602286067","https://openalex.org/W6607321472","https://openalex.org/W6661223370","https://openalex.org/W6666364710","https://openalex.org/W6703074907"],"related_works":["https://openalex.org/W2160402959","https://openalex.org/W56136284","https://openalex.org/W2352674739","https://openalex.org/W4237492828","https://openalex.org/W4309228610","https://openalex.org/W2783657965","https://openalex.org/W4248157169","https://openalex.org/W2002320519","https://openalex.org/W78181647","https://openalex.org/W3170128756"],"abstract_inverted_index":{"We":[0,122,161,183],"study":[1],"the":[2,45,50,58,75,87,91,97,100,129,135,149,153,157,167,180,190,194,207],"problem":[3,59,168],"of":[4,13,30,47,62,73,96,111,169],"generating":[5,23,74,171],"DAG-structured":[6,102],"category":[7,51,108],"hierarchies":[8],"over":[9],"a":[10,28,64,138],"given":[11],"set":[12,29,46],"documents":[14,48,83],"associated":[15,35],"with":[16,36],"\"importance\"":[17,77],"scores.":[18],"Example":[19],"application":[20],"includes":[21],"automatically":[22,170],"Wikipedia":[24,172],"disambiguation":[25,173],"pages":[26,174],"for":[27,79,127],"articles":[31],"having":[32],"click":[33],"counts":[34],"them.":[37],"Unlike":[38],"previous":[39],"works,":[40],"which":[41],"focus":[42],"on":[43,166],"clustering":[44],"using":[49,156,175],"hierarchy":[52,103],"as":[53,60,86,137,179,202],"features,":[54],"we":[55,113],"directly":[56],"pose":[57],"that":[61,69,185,199],"finding":[63],"DAG":[65,92,136],"structured":[66],"generative":[67,120],"mode":[68],"has":[70],"maximum":[71],"likelihood":[72],"observed":[76],"scores":[78],"each":[80,110],"document":[81,105],"where":[82],"are":[84,200],"modeled":[85,117],"leaf":[88],"nodes":[89],"in":[90,99],"structure.":[93],"Desirable":[94],"properties":[95],"categories":[98],"inferred":[101],"include":[104],"coverage":[106],"and":[107,141,148,197],"relevance,":[109],"which,":[112],"show,":[114],"is":[115],"naturally":[116],"by":[118,133,151],"our":[119,164,186],"model.":[121],"propose":[123],"two":[124],"different":[125],"algorithms":[126],"estimating":[128,142,152],"model":[130],"parameters.":[131],"One":[132],"modeling":[134],"Bayesian":[139],"Network":[140],"its":[143],"parameters":[144],"via":[145],"Gibbs":[146],"Sampling;":[147],"other":[150],"path":[154],"probabilities":[155],"Expectation":[158],"Maximization":[159],"algorithm.":[160],"empirically":[162],"evaluate":[163,206],"method":[165],"human":[176],"generated":[177],"clusterings":[178],"ground":[181],"truth.":[182],"find":[184],"framework":[187],"improves":[188],"upon":[189],"baselines":[191],"according":[192],"to":[193,205],"F1":[195],"score":[196],"Entropy":[198],"used":[201],"standard":[203],"metrics":[204],"hierarchical":[208],"clustering.":[209]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-10-28T00:00:00"}