{"id":"https://openalex.org/W2250865373","doi":"https://doi.org/10.18653/v1/d13-1069","title":"Automatically Determining a Proper Length for Multi-Document Summarization: A Bayesian Nonparametric Approach","display_name":"Automatically Determining a Proper Length for Multi-Document Summarization: A Bayesian Nonparametric Approach","publication_year":2013,"publication_date":"2013-01-01","ids":{"openalex":"https://openalex.org/W2250865373","doi":"https://doi.org/10.18653/v1/d13-1069","mag":"2250865373"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d13-1069","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/d13-1069","pdf_url":"https://aclanthology.org/D13-1069.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/D13-1069.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086690079","display_name":"Tengfei Ma","orcid":"https://orcid.org/0000-0002-1086-529X"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Tengfei Ma","raw_affiliation_strings":["The University of Tokyo 7-3-1 Hongo , Bunkyo-ku , Tokyo","The University of Tokyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo 7-3-1 Hongo , Bunkyo-ku , Tokyo","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020912760","display_name":"Hiroshi Nakagawa","orcid":"https://orcid.org/0000-0002-3024-9136"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi Nakagawa","raw_affiliation_strings":["The University of Tokyo 7-3-1 Hongo , Bunkyo-ku , Tokyo","Univ.\\ of Tokyo"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo 7-3-1 Hongo , Bunkyo-ku , Tokyo","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Univ.\\ of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5086690079"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":0.4944,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.78501106,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"736","last_page":"746"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9991000294685364,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9965000152587891,"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":0.9558313488960266},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.817603349685669},{"id":"https://openalex.org/keywords/minimum-description-length","display_name":"Minimum description length","score":0.6923954486846924},{"id":"https://openalex.org/keywords/multi-document-summarization","display_name":"Multi-document summarization","score":0.6176914572715759},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5771218538284302},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5102443695068359},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.487813264131546},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.44551706314086914},{"id":"https://openalex.org/keywords/nonparametric-statistics","display_name":"Nonparametric statistics","score":0.41246891021728516},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40762996673583984},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11868971586227417},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1184748113155365}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.9558313488960266},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.817603349685669},{"id":"https://openalex.org/C87465248","wikidata":"https://www.wikidata.org/wiki/Q1417790","display_name":"Minimum description length","level":2,"score":0.6923954486846924},{"id":"https://openalex.org/C134714966","wikidata":"https://www.wikidata.org/wiki/Q6934448","display_name":"Multi-document summarization","level":3,"score":0.6176914572715759},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5771218538284302},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5102443695068359},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.487813264131546},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.44551706314086914},{"id":"https://openalex.org/C102366305","wikidata":"https://www.wikidata.org/wiki/Q1097688","display_name":"Nonparametric statistics","level":2,"score":0.41246891021728516},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40762996673583984},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11868971586227417},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1184748113155365},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/d13-1069","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/d13-1069","pdf_url":"https://aclanthology.org/D13-1069.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.593.6727","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.593.6727","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://aclweb.org/anthology/D/D13/D13-1069.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.18653/v1/d13-1069","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/d13-1069","pdf_url":"https://aclanthology.org/D13-1069.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7900000214576721}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2250865373.pdf","grobid_xml":"https://content.openalex.org/works/W2250865373.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W152832198","https://openalex.org/W1512874001","https://openalex.org/W1517266559","https://openalex.org/W1529851927","https://openalex.org/W1663973292","https://openalex.org/W2001400305","https://openalex.org/W2034771957","https://openalex.org/W2037913249","https://openalex.org/W2082512208","https://openalex.org/W2083305840","https://openalex.org/W2099111195","https://openalex.org/W2105542801","https://openalex.org/W2115870554","https://openalex.org/W2117111086","https://openalex.org/W2121127148","https://openalex.org/W2128002512","https://openalex.org/W2132643852","https://openalex.org/W2141927646","https://openalex.org/W2148704041","https://openalex.org/W2150824314","https://openalex.org/W2158266063","https://openalex.org/W2218641061","https://openalex.org/W3101913037"],"related_works":["https://openalex.org/W3164984162","https://openalex.org/W2104677027","https://openalex.org/W2902627734","https://openalex.org/W2112885393","https://openalex.org/W2065541085","https://openalex.org/W2785821657","https://openalex.org/W2173208124","https://openalex.org/W2568827738","https://openalex.org/W1990695371","https://openalex.org/W2365100044"],"abstract_inverted_index":{"Document":[0],"summarization":[1,31,97],"is":[2,36,46,59,65],"an":[3,109],"important":[4,19],"task":[5],"in":[6,98],"the":[7,17,33,42,56,72,103,120,144,151,154],"area":[8],"of":[9,28,78,85,106,147,153],"natural":[10],"language":[11],"processing,":[12],"which":[13,80,126],"aims":[14],"to":[15,40,55,68,100,129],"extract":[16],"most":[18],"information":[20],"from":[21,115],"a":[22,26,48,62,91,123,131],"single":[23],"document":[24,111],"or":[25],"cluster":[27],"documents.In":[29],"various":[30],"tasks,":[32],"summary":[34,44],"length":[35,45,58,74,155],"manually":[37],"defined.However,":[38],"how":[39],"find":[41],"proper":[43,104],"quite":[47,82],"problem;":[49],"and":[50,139,150],"keeping":[51],"all":[52],"summaries":[53,70,149],"restricted":[54],"same":[57,73],"not":[60],"always":[61],"good":[63,132,145],"choice.It":[64],"obviously":[66],"improper":[67],"generate":[69],"with":[71],"for":[75,95],"two":[76],"clusters":[77],"documents":[79],"contain":[81],"different":[83],"quantity":[84],"information.In":[86],"this":[87],"paper,":[88],"we":[89,118],"propose":[90],"Bayesian":[92,124],"nonparametric":[93],"model":[94],"multidocument":[96],"order":[99],"automatically":[101],"determine":[102],"lengths":[105],"summaries.Assuming":[107],"that":[108],"original":[110],"can":[112],"be":[113],"reconstructed":[114],"its":[116],"summary,":[117],"describe":[119],"\"reconstruction\"":[121],"by":[122],"framework":[125],"selects":[127],"sentences":[128],"form":[130],"summary.Experimental":[133],"results":[134],"on":[135],"DUC2004":[136],"data":[137,142],"sets":[138],"some":[140],"expanded":[141],"demonstrate":[143],"quality":[146],"our":[148],"rationality":[152],"determination.":[156]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}