{"id":"https://openalex.org/W2797269287","doi":"https://doi.org/10.18653/v1/n18-2102","title":"Multi-Reward Reinforced Summarization with Saliency and Entailment","display_name":"Multi-Reward Reinforced Summarization with Saliency and Entailment","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2797269287","doi":"https://doi.org/10.18653/v1/n18-2102","mag":"2797269287"},"language":"en","primary_location":{"id":"doi:10.18653/v1/n18-2102","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/n18-2102","pdf_url":"https://www.aclweb.org/anthology/N18-2102.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 2018 Conference of the North American Chapter of\n          the Association for Computational Linguistics: Human Language\n          Technologies, Volume 2 (Short Papers)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/N18-2102.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075564427","display_name":"Ramakanth Pasunuru","orcid":null},"institutions":[{"id":"https://openalex.org/I1333535994","display_name":"University of North Carolina Health Care","ror":"https://ror.org/00qz24g20","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1333535994"]},{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ramakanth Pasunuru","raw_affiliation_strings":["UNC Chapel Hill","University of North Carolina at Chapel Hill, Chapel Hill, United States"],"affiliations":[{"raw_affiliation_string":"UNC Chapel Hill","institution_ids":["https://openalex.org/I1333535994","https://openalex.org/I114027177"]},{"raw_affiliation_string":"University of North Carolina at Chapel Hill, Chapel Hill, United States","institution_ids":["https://openalex.org/I114027177"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001987532","display_name":"Mohit Bansal","orcid":"https://orcid.org/0000-0001-5522-1351"},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]},{"id":"https://openalex.org/I1333535994","display_name":"University of North Carolina Health Care","ror":"https://ror.org/00qz24g20","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1333535994"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohit Bansal","raw_affiliation_strings":["UNC Chapel Hill","University of North Carolina at Chapel Hill, Chapel Hill, United States"],"affiliations":[{"raw_affiliation_string":"UNC Chapel Hill","institution_ids":["https://openalex.org/I1333535994","https://openalex.org/I114027177"]},{"raw_affiliation_string":"University of North Carolina at Chapel Hill, Chapel Hill, United States","institution_ids":["https://openalex.org/I114027177"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5075564427"],"corresponding_institution_ids":["https://openalex.org/I114027177","https://openalex.org/I1333535994"],"apc_list":null,"apc_paid":null,"fwci":7.7439359,"has_fulltext":true,"cited_by_count":47,"citation_normalized_percentile":{"value":0.97164497,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"646","last_page":"653"},"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":0.9997000098228455,"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":0.9997000098228455,"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":0.896034836769104},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.722736120223999},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6634730696678162},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6497437953948975},{"id":"https://openalex.org/keywords/logical-consequence","display_name":"Logical consequence","score":0.6490626335144043},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.6202923655509949},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.606047511100769},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5710596442222595},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.4955345392227173},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.4554954469203949},{"id":"https://openalex.org/keywords/textual-entailment","display_name":"Textual entailment","score":0.44805100560188293},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37625110149383545}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.896034836769104},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.722736120223999},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6634730696678162},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6497437953948975},{"id":"https://openalex.org/C134752490","wikidata":"https://www.wikidata.org/wiki/Q374182","display_name":"Logical consequence","level":2,"score":0.6490626335144043},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.6202923655509949},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.606047511100769},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5710596442222595},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.4955345392227173},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4554954469203949},{"id":"https://openalex.org/C95318506","wikidata":"https://www.wikidata.org/wiki/Q6588467","display_name":"Textual entailment","level":3,"score":0.44805100560188293},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37625110149383545},{"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/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/n18-2102","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/n18-2102","pdf_url":"https://www.aclweb.org/anthology/N18-2102.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 2018 Conference of the North American Chapter of\n          the Association for Computational Linguistics: Human Language\n          Technologies, Volume 2 (Short Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1804.06451","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1804.06451","pdf_url":"https://arxiv.org/pdf/1804.06451","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:2797269287","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1804.06451.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1804.06451","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1804.06451","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.18653/v1/n18-2102","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/n18-2102","pdf_url":"https://www.aclweb.org/anthology/N18-2102.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 2018 Conference of the North American Chapter of\n          the Association for Computational Linguistics: Human Language\n          Technologies, Volume 2 (Short Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2797269287.pdf","grobid_xml":"https://content.openalex.org/works/W2797269287.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W655477013","https://openalex.org/W806995027","https://openalex.org/W1577929347","https://openalex.org/W1843891098","https://openalex.org/W1939882552","https://openalex.org/W1964326564","https://openalex.org/W2112644606","https://openalex.org/W2115322217","https://openalex.org/W2133182690","https://openalex.org/W2133459682","https://openalex.org/W2148404145","https://openalex.org/W2154652894","https://openalex.org/W2164755781","https://openalex.org/W2176263492","https://openalex.org/W2204302769","https://openalex.org/W2250307601","https://openalex.org/W2250810255","https://openalex.org/W2251654079","https://openalex.org/W2251919380","https://openalex.org/W2252029281","https://openalex.org/W2341401723","https://openalex.org/W2413794162","https://openalex.org/W2427527485","https://openalex.org/W2467173223","https://openalex.org/W2525778437","https://openalex.org/W2560313346","https://openalex.org/W2573425638","https://openalex.org/W2586041121","https://openalex.org/W2606974598","https://openalex.org/W2607892599","https://openalex.org/W2612675303","https://openalex.org/W2621537751","https://openalex.org/W2626182443","https://openalex.org/W2742943414","https://openalex.org/W2757311323","https://openalex.org/W2797563284","https://openalex.org/W2949615363","https://openalex.org/W2950019912","https://openalex.org/W2953084091","https://openalex.org/W2964121744","https://openalex.org/W2964308564"],"related_works":["https://openalex.org/W2606974598","https://openalex.org/W2612675303","https://openalex.org/W2962884827","https://openalex.org/W2963403868","https://openalex.org/W2154652894","https://openalex.org/W1544827683","https://openalex.org/W2119717200","https://openalex.org/W2963929190","https://openalex.org/W2064675550","https://openalex.org/W2962985882","https://openalex.org/W2101105183","https://openalex.org/W2963084599","https://openalex.org/W2525778437","https://openalex.org/W2157331557","https://openalex.org/W2889518897","https://openalex.org/W2964308564","https://openalex.org/W2963248296","https://openalex.org/W648786980","https://openalex.org/W2962965405","https://openalex.org/W2574535369"],"abstract_inverted_index":{"Abstractive":[0],"text":[1],"summarization":[2],"is":[3],"the":[4,61,66,123,131],"task":[5],"of":[6,34,53,112],"compressing":[7],"and":[8,23,49,108],"rewriting":[9],"a":[10,14,35,39,54,71,141],"long":[11],"document":[12],"into":[13],"short":[15],"summary":[16,37],"while":[17],"maintaining":[18],"saliency,":[19],"directed":[20],"logical":[21],"entailment,":[22],"non-redundancy.":[24],"In":[25],"this":[26],"work,":[27],"we":[28,89],"address":[29],"these":[30,95],"three":[31],"important":[32],"aspects":[33],"good":[36],"via":[38,70,105],"reinforcement":[40],"learning":[41],"approach":[42,111],"with":[43,99],"two":[44],"novel":[45,107],"reward":[46,59,76],"functions:":[47],"ROUGESal":[48,58],"Entail,":[50],"on":[51,130,145],"top":[52],"coverage-based":[55],"baseline.":[56],"The":[57,74],"modifies":[60],"ROUGE":[62],"metric":[63,101],"by":[64],"up-weighting":[65],"salient":[67],"phrases/words":[68],"detected":[69],"keyphrase":[72],"classifier.":[73,87],"Entail":[75],"gives":[77],"high":[78],"(length-normalized)":[79],"scores":[80],"to":[81],"logically-entailed":[82],"summaries":[83],"using":[84],"an":[85],"entailment":[86],"Further,":[88],"show":[90],"superior":[91],"performance":[92],"improvement":[93],"when":[94],"rewards":[96,115],"are":[97],"combined":[98],"traditional":[100],"(ROUGE)":[102],"based":[103],"rewards,":[104],"our":[106],"effective":[109],"multi-reward":[110],"optimizing":[113],"multiple":[114],"simultaneously":[116],"in":[117,140],"alternate":[118],"mini-batches.":[119],"Our":[120],"method":[121],"achieves":[122],"new":[124],"state-of-the-art":[125],"results":[126],"(including":[127],"human":[128],"evaluation)":[129],"CNN/Daily":[132],"Mail":[133],"dataset":[134],"as":[135,137],"well":[136],"strong":[138],"improvements":[139],"test-only":[142],"transfer":[143],"setup":[144],"DUC-2002.":[146]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":18},{"year":2019,"cited_by_count":11},{"year":2018,"cited_by_count":3}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}