{"id":"https://openalex.org/W2890721473","doi":"https://doi.org/10.18653/v1/d18-1448","title":"MSMO: Multimodal Summarization with Multimodal Output","display_name":"MSMO: Multimodal Summarization with Multimodal Output","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2890721473","doi":"https://doi.org/10.18653/v1/d18-1448","mag":"2890721473"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d18-1448","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1448","pdf_url":"https://www.aclweb.org/anthology/D18-1448.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 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://www.aclweb.org/anthology/D18-1448.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015809194","display_name":"Junnan Zhu","orcid":"https://orcid.org/0000-0002-9856-2946"},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Junnan Zhu","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Institute of Automation, CAS, Beijing, China","University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, CAS, Beijing, China","institution_ids":["https://openalex.org/I4210094879"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100327720","display_name":"Haoran Li","orcid":"https://orcid.org/0000-0002-2368-7541"},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoran Li","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Institute of Automation, CAS, Beijing, China","University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, CAS, Beijing, China","institution_ids":["https://openalex.org/I4210094879"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060038422","display_name":"Tianshang Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianshang Liu","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Institute of Automation, CAS, Beijing, China","University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, CAS, Beijing, China","institution_ids":["https://openalex.org/I4210094879"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018062280","display_name":"Yu Zhou","orcid":"https://orcid.org/0000-0002-0304-0863"},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Zhou","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Institute of Automation, CAS, Beijing, China","University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, CAS, Beijing, China","institution_ids":["https://openalex.org/I4210094879"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100319572","display_name":"Jiajun Zhang","orcid":"https://orcid.org/0000-0001-5293-7434"},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiajun Zhang","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Institute of Automation, CAS, Beijing, China","University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, CAS, Beijing, China","institution_ids":["https://openalex.org/I4210094879"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015785439","display_name":"Chengqing Zong","orcid":"https://orcid.org/0000-0002-9864-3818"},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210097554","display_name":"Center for Excellence in Brain Science and Intelligence Technology","ror":"https://ror.org/00vpwhm04","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210097554"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengqing Zong","raw_affiliation_strings":["CAS Center for Excellence in Brain Science and Intelligence Technology, Beijing, China","National Laboratory of Pattern Recognition, Institute of Automation, CAS, Beijing, China","University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CAS Center for Excellence in Brain Science and Intelligence Technology, Beijing, China","institution_ids":["https://openalex.org/I4210097554"]},{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, CAS, Beijing, China","institution_ids":["https://openalex.org/I4210094879"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5015809194"],"corresponding_institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":8.8001,"has_fulltext":true,"cited_by_count":178,"citation_normalized_percentile":{"value":0.98140888,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"4154","last_page":"4164"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9965999722480774,"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":0.9592875242233276},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8579021096229553},{"id":"https://openalex.org/keywords/salience","display_name":"Salience (neuroscience)","score":0.6192135810852051},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5577933192253113},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5557385087013245},{"id":"https://openalex.org/keywords/multimodal-therapy","display_name":"Multimodal therapy","score":0.5468400120735168},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.5446630120277405},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5330841541290283},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4905552268028259},{"id":"https://openalex.org/keywords/multimodal-learning","display_name":"Multimodal learning","score":0.4408009350299835},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34549766778945923},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3316909074783325}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.9592875242233276},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8579021096229553},{"id":"https://openalex.org/C108154423","wikidata":"https://www.wikidata.org/wiki/Q1469792","display_name":"Salience (neuroscience)","level":2,"score":0.6192135810852051},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5577933192253113},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5557385087013245},{"id":"https://openalex.org/C4441509","wikidata":"https://www.wikidata.org/wiki/Q6418787","display_name":"Multimodal therapy","level":2,"score":0.5468400120735168},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.5446630120277405},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5330841541290283},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4905552268028259},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.4408009350299835},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34549766778945923},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3316909074783325},{"id":"https://openalex.org/C141071460","wikidata":"https://www.wikidata.org/wiki/Q40821","display_name":"Surgery","level":1,"score":0.0},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/d18-1448","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1448","pdf_url":"https://www.aclweb.org/anthology/D18-1448.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 on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/d18-1448","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1448","pdf_url":"https://www.aclweb.org/anthology/D18-1448.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 on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.5,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2890721473.pdf","grobid_xml":"https://content.openalex.org/works/W2890721473.grobid-xml"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1520857482","https://openalex.org/W1527575280","https://openalex.org/W1544827683","https://openalex.org/W1686810756","https://openalex.org/W1902237438","https://openalex.org/W1905882502","https://openalex.org/W1973894278","https://openalex.org/W2026012689","https://openalex.org/W2060724430","https://openalex.org/W2093541376","https://openalex.org/W2128629010","https://openalex.org/W2133564696","https://openalex.org/W2154652894","https://openalex.org/W2158899491","https://openalex.org/W2171447090","https://openalex.org/W2182959134","https://openalex.org/W2185175083","https://openalex.org/W2259890326","https://openalex.org/W2317486713","https://openalex.org/W2365919995","https://openalex.org/W2461084364","https://openalex.org/W2526278568","https://openalex.org/W2529165750","https://openalex.org/W2558173469","https://openalex.org/W2606473278","https://openalex.org/W2606974598","https://openalex.org/W2612675303","https://openalex.org/W2759570332","https://openalex.org/W2774267535","https://openalex.org/W2781963152","https://openalex.org/W2808413133","https://openalex.org/W2809191921","https://openalex.org/W2949615363","https://openalex.org/W2952230511","https://openalex.org/W2962835968","https://openalex.org/W2962965405","https://openalex.org/W2963385935","https://openalex.org/W2963768805","https://openalex.org/W2963929190","https://openalex.org/W2964308564","https://openalex.org/W3101913037","https://openalex.org/W3110683067","https://openalex.org/W4302444966"],"related_works":["https://openalex.org/W4307308932","https://openalex.org/W2949519365","https://openalex.org/W3157841754","https://openalex.org/W4381827277","https://openalex.org/W4390136517","https://openalex.org/W3167558523","https://openalex.org/W3120825179","https://openalex.org/W3092201840","https://openalex.org/W2014028898","https://openalex.org/W4384202059"],"abstract_inverted_index":{"Multimodal":[0],"summarization":[1,20,54],"has":[2],"drawn":[3],"much":[4],"attention":[5,77],"due":[6],"to":[7,79,94],"the":[8,17,85,90,119],"rapid":[9],"growth":[10],"of":[11,16,43,121],"multimedia":[12],"data.":[13],"The":[14,115],"output":[15,35,57],"current":[18],"multimodal":[19,34,53,56,76,91,96,102],"systems":[21],"is":[22],"usually":[23],"represented":[24],"in":[25],"texts.":[26],"However,":[27],"we":[28,48,63,98],"have":[29],"found":[30],"through":[31],"experiments":[32],"that":[33],"can":[36],"significantly":[37],"improve":[38],"user":[39],"satisfaction":[40],"for":[41,69],"informativeness":[42],"summaries.":[44],"In":[45],"this":[46,61],"paper,":[47],"propose":[49,74],"a":[50,66,75,100],"novel":[51,101],"task,":[52,62],"with":[55],"(MSMO).":[58],"To":[59],"handle":[60],"first":[64],"collect":[65],"large-scale":[67],"dataset":[68],"MSMO":[70],"research.":[71],"We":[72],"then":[73],"model":[78],"jointly":[80],"generate":[81],"text":[82],"and":[83,112],"select":[84],"most":[86],"relevant":[87],"image":[88],"from":[89],"input.":[92],"Finally,":[93],"evaluate":[95],"outputs,":[97],"construct":[99],"automatic":[103],"evaluation":[104],"(MMAE)":[105],"method":[106],"which":[107],"considers":[108],"both":[109],"intramodality":[110],"salience":[111],"intermodality":[113],"relevance.":[114],"experimental":[116],"results":[117],"show":[118],"effectiveness":[120],"MMAE.":[122]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":24},{"year":2024,"cited_by_count":32},{"year":2023,"cited_by_count":38},{"year":2022,"cited_by_count":26},{"year":2021,"cited_by_count":31},{"year":2020,"cited_by_count":16},{"year":2019,"cited_by_count":5}],"updated_date":"2026-06-02T09:04:35.204637","created_date":"2025-10-10T00:00:00"}