{"id":"https://openalex.org/W2251656679","doi":"https://doi.org/10.3115/v1/p15-1054","title":"Summarization of Multi-Document Topic Hierarchies using Submodular Mixtures","display_name":"Summarization of Multi-Document Topic Hierarchies using Submodular Mixtures","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2251656679","doi":"https://doi.org/10.3115/v1/p15-1054","mag":"2251656679"},"language":"en","primary_location":{"id":"doi:10.3115/v1/p15-1054","is_oa":false,"landing_page_url":"https://doi.org/10.3115/v1/p15-1054","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)","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":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ramakrishna Bairi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000529247","display_name":"Rishabh Iyer","orcid":"https://orcid.org/0000-0001-9851-463X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rishabh Iyer","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089606464","display_name":"Ganesh Ramakrishnan","orcid":"https://orcid.org/0000-0003-4533-2490"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ganesh Ramakrishnan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5113478221","display_name":"Jeff Bilmes","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jeff Bilmes","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5063416855"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.4515,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.93592697,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"553","last_page":"563"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9994000196456909,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9994000196456909,"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/T10028","display_name":"Topic Modeling","score":0.9966999888420105,"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":0.9952999949455261,"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/submodular-set-function","display_name":"Submodular set function","score":0.9615362882614136},{"id":"https://openalex.org/keywords/jaccard-index","display_name":"Jaccard index","score":0.8365638256072998},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7858452796936035},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.7743622064590454},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6020412445068359},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.5417007803916931},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5330703854560852},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.5305806994438171},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.498213529586792},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.4756995141506195},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4034273028373718},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3916342854499817},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.258317768573761},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14852675795555115}],"concepts":[{"id":"https://openalex.org/C178621042","wikidata":"https://www.wikidata.org/wiki/Q7631710","display_name":"Submodular set function","level":2,"score":0.9615362882614136},{"id":"https://openalex.org/C203519979","wikidata":"https://www.wikidata.org/wiki/Q865360","display_name":"Jaccard index","level":3,"score":0.8365638256072998},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7858452796936035},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.7743622064590454},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6020412445068359},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.5417007803916931},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5330703854560852},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5305806994438171},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.498213529586792},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.4756995141506195},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4034273028373718},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3916342854499817},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.258317768573761},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14852675795555115},{"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/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3115/v1/p15-1054","is_oa":false,"landing_page_url":"https://doi.org/10.3115/v1/p15-1054","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7200000286102295,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W52746146","https://openalex.org/W55768394","https://openalex.org/W177984263","https://openalex.org/W1486950299","https://openalex.org/W1510950165","https://openalex.org/W1532325895","https://openalex.org/W1548663377","https://openalex.org/W1598683382","https://openalex.org/W1680189815","https://openalex.org/W1880262756","https://openalex.org/W1898824936","https://openalex.org/W1962684803","https://openalex.org/W1984985727","https://openalex.org/W2022166150","https://openalex.org/W2031046392","https://openalex.org/W2033227606","https://openalex.org/W2052684427","https://openalex.org/W2061820396","https://openalex.org/W2094728533","https://openalex.org/W2102150019","https://openalex.org/W2106490775","https://openalex.org/W2108598243","https://openalex.org/W2111336742","https://openalex.org/W2112050062","https://openalex.org/W2113855231","https://openalex.org/W2123142779","https://openalex.org/W2125653933","https://openalex.org/W2127723919","https://openalex.org/W2131357087","https://openalex.org/W2132827946","https://openalex.org/W2134267347","https://openalex.org/W2135140174","https://openalex.org/W2144933361","https://openalex.org/W2150766729","https://openalex.org/W2155440340","https://openalex.org/W2158266063","https://openalex.org/W2161160262","https://openalex.org/W2169463693","https://openalex.org/W2251590347","https://openalex.org/W2521110248","https://openalex.org/W2963241965"],"related_works":["https://openalex.org/W4254879869","https://openalex.org/W3022576529","https://openalex.org/W2628526247","https://openalex.org/W2596401011","https://openalex.org/W2963844234","https://openalex.org/W2803250016","https://openalex.org/W2138952379","https://openalex.org/W2953050252","https://openalex.org/W2093888054","https://openalex.org/W4226263291"],"abstract_inverted_index":{"We":[0,141,156,177],"study":[1],"the":[2,53,58,66,78,85,135,151,162,195],"problem":[3,67,72,163],"of":[4,13,26,55,84,98,153,164,190],"summarizing":[5],"DAG-structured":[6],"topic":[7,59,75,92,95],"hierarchies":[8],"over":[9,150],"a":[10,24,69,74,106,128,143,188],"given":[11],"set":[12,25,54,152],"documents.":[14],"Example":[15],"applications":[16],"include":[17,88],"automatically":[18,165],"generating":[19,29,166],"Wikipedia":[20,167],"disambiguation":[21,168],"pages":[22,169],"for":[23,32,38],"articles,":[27],"and":[28,43,94,119,138,200,202],"candidate":[30],"multi-labels":[31],"preparing":[33],"machine":[34],"learning":[35],"datasets":[36],"(e.g.,":[37],"text":[39],"classification,":[40],"functional":[41],"genomics,":[42],"image":[44],"classification).":[45],"Unlike":[46],"previous":[47],"work,":[48],"which":[49],"focuses":[50],"on":[51,73,161],"clustering":[52],"documents":[56,79],"using":[57,77,170],"hierarchy":[60,76],"as":[61,68,80,117,174],"features,":[62],"we":[63,100],"directly":[64],"pose":[65],"submodular":[70,107,129,154],"optimization":[71],"features.":[81],"Desirable":[82],"properties":[83],"chosen":[86,136],"topics":[87,137],"document":[89],"coverage,":[90],"specificity,":[91],"diversity,":[93],"homogeneity,":[96],"each":[97],"which,":[99],"show,":[101],"is":[102],"naturally":[103],"modeled":[104],"by":[105,113,126],"function.":[108],"Other":[109],"information,":[110],"provided":[111],"say":[112],"unsupervised":[114],"approaches":[115],"such":[116],"LDA":[118],"its":[120],"variants,":[121],"can":[122,204],"also":[123],"be":[124,205],"utilized":[125],"defining":[127],"function":[130],"that":[131,179],"expresses":[132],"coherence":[133],"between":[134],"this":[139],"information.":[140],"use":[142],"large-margin":[144],"framework":[145,181],"to":[146,187,207],"learn":[147],"convex":[148],"mixtures":[149],"components.":[155],"empirically":[157],"evaluate":[158],"our":[159,180],"method":[160],"human":[171],"generated":[172],"clusterings":[173],"ground":[175],"truth.":[176],"find":[178],"improves":[182],"upon":[183],"several":[184],"baselines":[185],"according":[186],"variety":[189],"standard":[191],"evaluation":[192],"metrics":[193],"including":[194],"Jaccard":[196],"Index,":[197],"F1":[198],"score":[199],"NMI,":[201],"moreover,":[203],"scaled":[206],"extremely":[208],"large":[209],"scale":[210],"problems.":[211]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}