{"id":"https://openalex.org/W3098913828","doi":"https://doi.org/10.18653/v1/2020.emnlp-main.136","title":"Multi-document Summarization with Maximal Marginal Relevance-guided Reinforcement Learning","display_name":"Multi-document Summarization with Maximal Marginal Relevance-guided Reinforcement Learning","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3098913828","doi":"https://doi.org/10.18653/v1/2020.emnlp-main.136","mag":"3098913828"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2020.emnlp-main.136","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.emnlp-main.136","pdf_url":"https://www.aclweb.org/anthology/2020.emnlp-main.136.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 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/2020.emnlp-main.136.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012370787","display_name":"Yuning Mao","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yuning Mao","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037311972","display_name":"Yanru Qu","orcid":"https://orcid.org/0000-0002-7664-0421"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yanru Qu","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085030899","display_name":"Yiqing Xie","orcid":"https://orcid.org/0000-0002-1668-0376"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yiqing Xie","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009408707","display_name":"Xiang Ren","orcid":"https://orcid.org/0000-0001-8655-663X"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiang Ren","raw_affiliation_strings":["University of Southern California, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019539533","display_name":"Jiawei Han","orcid":"https://orcid.org/0000-0002-3629-2696"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiawei Han","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5012370787"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":4.35,"has_fulltext":true,"cited_by_count":43,"citation_normalized_percentile":{"value":0.95374617,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1737","last_page":"1751"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":1.0,"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":1.0,"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":0.9932000041007996,"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":0.9284241795539856},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.758662223815918},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7576744556427002},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.7478118538856506},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.601385772228241},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5647258758544922},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5605573654174805},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.49362051486968994},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.47537246346473694},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.46712547540664673}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.9284241795539856},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.758662223815918},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7576744556427002},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.7478118538856506},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.601385772228241},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5647258758544922},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5605573654174805},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49362051486968994},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.47537246346473694},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.46712547540664673},{"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/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2020.emnlp-main.136","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.emnlp-main.136","pdf_url":"https://www.aclweb.org/anthology/2020.emnlp-main.136.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 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2020.emnlp-main.136","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.emnlp-main.136","pdf_url":"https://www.aclweb.org/anthology/2020.emnlp-main.136.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 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.4099999964237213,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1472423617","display_name":null,"funder_award_id":"FA8750-19-2-1004","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G2104517209","display_name":null,"funder_award_id":"IIS-17-41317","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3688555466","display_name":null,"funder_award_id":"IIS-19-56151, IIS-17-41317, IIS 17-04532","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G427511869","display_name":null,"funder_award_id":"IIS 17-04532","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4713059963","display_name":null,"funder_award_id":"FA8750","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G5490100290","display_name":null,"funder_award_id":"HDTRA11810026","funder_id":"https://openalex.org/F4320332186","funder_display_name":"Defense Threat Reduction Agency"},{"id":"https://openalex.org/G6445402324","display_name":null,"funder_award_id":"IIS-19-56151","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6541015203","display_name":null,"funder_award_id":"HDTRA1","funder_id":"https://openalex.org/F4320332186","funder_display_name":"Defense Threat Reduction Agency"},{"id":"https://openalex.org/G7903051118","display_name":null,"funder_award_id":"IIS 16-18481","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8175839138","display_name":null,"funder_award_id":"No. W911NF-17-C-0099","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8851674072","display_name":null,"funder_award_id":"W911NF-17-C-0099","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320332186","display_name":"Defense Threat Reduction Agency","ror":"https://ror.org/04tz64554"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3098913828.pdf","grobid_xml":"https://content.openalex.org/works/W3098913828.grobid-xml"},"referenced_works_count":52,"referenced_works":["https://openalex.org/W1832693441","https://openalex.org/W1939882552","https://openalex.org/W1940872118","https://openalex.org/W1975579663","https://openalex.org/W1989420837","https://openalex.org/W2102269292","https://openalex.org/W2110693578","https://openalex.org/W2118733980","https://openalex.org/W2119717200","https://openalex.org/W2138779671","https://openalex.org/W2150869743","https://openalex.org/W2154652894","https://openalex.org/W2170344111","https://openalex.org/W2250829779","https://openalex.org/W2559730228","https://openalex.org/W2574535369","https://openalex.org/W2604777655","https://openalex.org/W2606974598","https://openalex.org/W2612675303","https://openalex.org/W2741375528","https://openalex.org/W2757254625","https://openalex.org/W2785994986","https://openalex.org/W2808293684","https://openalex.org/W2865911429","https://openalex.org/W2902706465","https://openalex.org/W2952138241","https://openalex.org/W2962946054","https://openalex.org/W2962966181","https://openalex.org/W2962972512","https://openalex.org/W2962985882","https://openalex.org/W2963173796","https://openalex.org/W2963341956","https://openalex.org/W2963548995","https://openalex.org/W2963569619","https://openalex.org/W2963716836","https://openalex.org/W2963768805","https://openalex.org/W2963929190","https://openalex.org/W2964144561","https://openalex.org/W2964609953","https://openalex.org/W2970390610","https://openalex.org/W2970419734","https://openalex.org/W2970785793","https://openalex.org/W2977796275","https://openalex.org/W2996264288","https://openalex.org/W3012910066","https://openalex.org/W3034266472","https://openalex.org/W3034715004","https://openalex.org/W3034999214","https://openalex.org/W3101913037","https://openalex.org/W3102612524","https://openalex.org/W3103014337","https://openalex.org/W3138773240"],"related_works":["https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W1490753184","https://openalex.org/W2284465472","https://openalex.org/W2291782699","https://openalex.org/W1993948687","https://openalex.org/W2000169967","https://openalex.org/W2112883198"],"abstract_inverted_index":{"While":[0],"neural":[1,47,90,129],"sequence":[2],"learning":[3,161,171],"methods":[4,48,67,92],"have":[5],"made":[6],"significant":[7],"progress":[8],"in":[9,97,125,167],"single-document":[10],"summarization":[11,19],"(SDS),":[12],"they":[13],"produce":[14],"unsatisfactory":[15],"results":[16],"on":[17,104,146],"multi-document":[18],"(MDS).":[20],"We":[21],"observe":[22],"two":[23],"major":[24],"challenges":[25],"when":[26,162],"adapting":[27,163],"SDS":[28,66,91,164],"advances":[29],"to":[30,49,56,71,116,134,165],"MDS:":[31],"(1)":[32],"MDS":[33,54,148,166],"involves":[34],"larger":[35],"search":[36,111],"space":[37,112],"and":[38,93,113,173],"yet":[39],"more":[40],"limited":[41],"training":[42],"data,":[43],"setting":[44],"obstacles":[45],"for":[46,85],"learn":[50],"adequate":[51],"representations;":[52],"(2)":[53],"needs":[55],"resolve":[57],"higher":[58],"information":[59],"redundancy":[60,123],"among":[61],"the":[62,75,110,121,128,132,154],"source":[63],"documents,":[64],"which":[65,87,108],"are":[68],"less":[69],"effective":[70],"handle.":[72],"To":[73],"close":[74],"gap,":[76],"we":[77,152],"present":[78],"RL-MMR,":[79],"Maximal":[80],"Margin":[81],"Relevance-guided":[82],"Reinforcement":[83],"Learning":[84],"MDS,":[86],"unifies":[88],"advanced":[89],"statistical":[94],"measures":[95],"used":[96],"classical":[98],"MDS.":[99],"RL-MMR":[100,142],"casts":[101],"MMR":[102,126,158],"guidance":[103],"fewer":[105],"promising":[106],"candidates,":[107],"restrains":[109],"thus":[114],"leads":[115],"better":[117,135],"representation":[118,130],"learning.":[119],"Additionally,":[120],"explicit":[122],"measure":[124],"helps":[127],"of":[131,156,169],"summary":[133],"capture":[136],"redundancy.":[137],"Extensive":[138],"experiments":[139],"demonstrate":[140],"that":[141],"achieves":[143],"state-of-the-art":[144],"performance":[145],"benchmark":[147],"datasets.":[149],"In":[150],"particular,":[151],"show":[153],"benefits":[155],"incorporating":[157],"into":[159],"end-to-end":[160],"terms":[168],"both":[170],"effectiveness":[172],"efficiency.":[174],"1":[175]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}