{"id":"https://openalex.org/W2151343603","doi":"https://doi.org/10.1145/1390749.1390764","title":"Latent dirichlet allocation based multi-document summarization","display_name":"Latent dirichlet allocation based multi-document summarization","publication_year":2008,"publication_date":"2008-07-24","ids":{"openalex":"https://openalex.org/W2151343603","doi":"https://doi.org/10.1145/1390749.1390764","mag":"2151343603"},"language":"en","primary_location":{"id":"doi:10.1145/1390749.1390764","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1390749.1390764","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the second workshop on Analytics for noisy unstructured text data","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/A5061046877","display_name":"Rachit Arora","orcid":null},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"facility","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Rachit Arora","raw_affiliation_strings":["Indian Institute of Technology, Madras, Chennai, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology, Madras, Chennai, India","institution_ids":["https://openalex.org/I24676775"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009374923","display_name":"Balaraman Ravindran","orcid":"https://orcid.org/0000-0002-5364-7639"},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"facility","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Balaraman Ravindran","raw_affiliation_strings":["Indian Institute of Technology, Madras, Chennai, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology, Madras, Chennai, India","institution_ids":["https://openalex.org/I24676775"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5061046877"],"corresponding_institution_ids":["https://openalex.org/I24676775"],"apc_list":null,"apc_paid":null,"fwci":8.7988,"has_fulltext":false,"cited_by_count":110,"citation_normalized_percentile":{"value":0.97542177,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"91","last_page":"97"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9998000264167786,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.996999979019165,"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/automatic-summarization","display_name":"Automatic summarization","score":0.9540582895278931},{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.9443380832672119},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.827345073223114},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6554572582244873},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5860273838043213},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.5748288035392761},{"id":"https://openalex.org/keywords/grammar","display_name":"Grammar","score":0.5694084167480469},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.5454815030097961},{"id":"https://openalex.org/keywords/multi-document-summarization","display_name":"Multi-document summarization","score":0.5180816650390625},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5150573253631592},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.4526434540748596},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.4504311680793762},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10146826505661011}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.9540582895278931},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.9443380832672119},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.827345073223114},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6554572582244873},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5860273838043213},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.5748288035392761},{"id":"https://openalex.org/C26022165","wikidata":"https://www.wikidata.org/wiki/Q8091","display_name":"Grammar","level":2,"score":0.5694084167480469},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.5454815030097961},{"id":"https://openalex.org/C134714966","wikidata":"https://www.wikidata.org/wiki/Q6934448","display_name":"Multi-document summarization","level":3,"score":0.5180816650390625},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5150573253631592},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.4526434540748596},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.4504311680793762},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10146826505661011},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1390749.1390764","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1390749.1390764","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the second workshop on Analytics for noisy unstructured text data","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.161.7083","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.161.7083","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-all.cs.umass.edu/~ravi/papers/Rachit-AND08.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1880262756","https://openalex.org/W1915058860","https://openalex.org/W1983249544","https://openalex.org/W2001082470","https://openalex.org/W2106490775","https://openalex.org/W2107034620","https://openalex.org/W2108325777","https://openalex.org/W2110656997","https://openalex.org/W2122678284","https://openalex.org/W2132484736","https://openalex.org/W2147590203","https://openalex.org/W2149035855","https://openalex.org/W2150824314","https://openalex.org/W2154652894","https://openalex.org/W2158266063","https://openalex.org/W6639619044","https://openalex.org/W6681769576","https://openalex.org/W6682631176"],"related_works":["https://openalex.org/W2769501189","https://openalex.org/W4315588616","https://openalex.org/W4312773271","https://openalex.org/W2888805565","https://openalex.org/W2962686197","https://openalex.org/W2104677027","https://openalex.org/W3005513013","https://openalex.org/W2207653751","https://openalex.org/W3164984162","https://openalex.org/W2611137333"],"abstract_inverted_index":{"Extraction":[0],"based":[1],"Multi-Document":[2],"Summarization":[3],"Algorithms":[4],"consist":[5],"of":[6,77,81,89],"choosing":[7],"sentences":[8,44,70],"from":[9,53],"the":[10,32,37,41,64,69,75,82,87,90,93,101,106],"documents":[11,38],"using":[12,100],"some":[13],"weighting":[14],"mechanism":[15],"and":[16,39,66,79],"combining":[17],"them":[18],"into":[19],"a":[20],"summary.":[21],"In":[22],"this":[23],"article":[24],"we":[25,58,85],"use":[26,59],"Latent":[27],"Dirichlet":[28],"Allocation":[29],"to":[30,62,74,104,109],"capture":[31,63],"events":[33],"being":[34],"covered":[35],"by":[36],"form":[40],"summary":[42],"with":[43],"representing":[45],"these":[46],"different":[47],"events.":[48],"Our":[49],"approach":[50],"is":[51],"distinguished":[52],"existing":[54],"approaches":[55],"in":[56],"that":[57],"mixture":[60],"models":[61],"topics":[65],"pick":[67],"up":[68],"without":[71],"paying":[72],"attention":[73],"details":[76],"grammar":[78],"structure":[80],"documents.":[83],"Finally":[84],"present":[86],"evaluation":[88],"algorithms":[91,114],"on":[92],"DUC":[94,110],"2002":[95,111],"Corpus":[96],"multi-document":[97],"summarization":[98],"tasks":[99],"ROUGE":[102],"evaluator":[103],"evaluate":[105],"summaries.":[107],"Compared":[108],"winners,":[112],"our":[113],"gave":[115],"significantly":[116],"better":[117],"ROUGE-1":[118],"recall":[119],"measures.":[120]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":13},{"year":2016,"cited_by_count":13},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":10},{"year":2013,"cited_by_count":9},{"year":2012,"cited_by_count":9}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}