{"id":"https://openalex.org/W4387398451","doi":"https://doi.org/10.1145/3606368","title":"Multimodal Dialog Systems with Dual Knowledge-enhanced Generative Pretrained Language Model","display_name":"Multimodal Dialog Systems with Dual Knowledge-enhanced Generative Pretrained Language Model","publication_year":2023,"publication_date":"2023-10-06","ids":{"openalex":"https://openalex.org/W4387398451","doi":"https://doi.org/10.1145/3606368"},"language":"en","primary_location":{"id":"doi:10.1145/3606368","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3606368","pdf_url":null,"source":{"id":"https://openalex.org/S4394735545","display_name":"ACM Transactions on Information Systems","issn_l":"1046-8188","issn":["1046-8188","1558-2868"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Information Systems","raw_type":"journal-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/A5100693591","display_name":"Xiaolin Chen","orcid":"https://orcid.org/0000-0003-4638-0603"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaolin Chen","raw_affiliation_strings":["School of Software, Joint SDU-NTU Centre for Artificial Intelligence Research, Shandong University, China"],"raw_orcid":"https://orcid.org/0000-0003-4638-0603","affiliations":[{"raw_affiliation_string":"School of Software, Joint SDU-NTU Centre for Artificial Intelligence Research, Shandong University, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072768866","display_name":"Xuemeng Song","orcid":"https://orcid.org/0000-0002-5274-4197"},"institutions":[{"id":"https://openalex.org/I80143920","display_name":"Shandong University of Science and Technology","ror":"https://ror.org/04gtjhw98","country_code":"CN","type":"education","lineage":["https://openalex.org/I80143920"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuemeng Song","raw_affiliation_strings":["School of Computer Science and Technology, Shandong University, China"],"raw_orcid":"https://orcid.org/0000-0002-5274-4197","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Shandong University, China","institution_ids":["https://openalex.org/I80143920"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051341911","display_name":"Liqiang Jing","orcid":"https://orcid.org/0000-0001-9827-5835"},"institutions":[{"id":"https://openalex.org/I80143920","display_name":"Shandong University of Science and Technology","ror":"https://ror.org/04gtjhw98","country_code":"CN","type":"education","lineage":["https://openalex.org/I80143920"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liqiang Jing","raw_affiliation_strings":["School of Computer Science and Technology, Shandong University, China"],"raw_orcid":"https://orcid.org/0000-0001-9827-5835","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Shandong University, China","institution_ids":["https://openalex.org/I80143920"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100386668","display_name":"Shuo Li","orcid":"https://orcid.org/0009-0000-2204-2066"},"institutions":[{"id":"https://openalex.org/I80143920","display_name":"Shandong University of Science and Technology","ror":"https://ror.org/04gtjhw98","country_code":"CN","type":"education","lineage":["https://openalex.org/I80143920"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuo Li","raw_affiliation_strings":["School of Computer Science and Technology, Shandong University, China"],"raw_orcid":"https://orcid.org/0009-0000-2204-2066","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Shandong University, China","institution_ids":["https://openalex.org/I80143920"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063307425","display_name":"Linmei Hu","orcid":"https://orcid.org/0000-0003-0993-8495"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linmei Hu","raw_affiliation_strings":["School of Computer Science and Technology, Beijing Institute of Technology, China"],"raw_orcid":"https://orcid.org/0000-0003-0993-8495","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Beijing Institute of Technology, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038612499","display_name":"Liqiang Nie","orcid":"https://orcid.org/0000-0003-1476-0273"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liqiang Nie","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), China"],"raw_orcid":"https://orcid.org/0000-0003-1476-0273","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.8553,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.92185987,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"42","issue":"2","first_page":"1","last_page":"25"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T12031","display_name":"Speech and dialogue systems","score":0.9937999844551086,"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/dialog-box","display_name":"Dialog box","score":0.7710183262825012},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7629722356796265},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6399186849594116},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.5930286645889282},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.5719422101974487},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5630436539649963},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5372633337974548},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4761084020137787},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.46894997358322144},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4526689648628235},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.43802398443222046},{"id":"https://openalex.org/keywords/dialog-system","display_name":"Dialog system","score":0.4198623299598694},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.33051109313964844},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11462318897247314},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07815921306610107},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.06743815541267395}],"concepts":[{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.7710183262825012},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7629722356796265},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6399186849594116},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.5930286645889282},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.5719422101974487},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5630436539649963},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5372633337974548},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4761084020137787},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.46894997358322144},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4526689648628235},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.43802398443222046},{"id":"https://openalex.org/C190954187","wikidata":"https://www.wikidata.org/wiki/Q5270587","display_name":"Dialog system","level":3,"score":0.4198623299598694},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33051109313964844},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11462318897247314},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07815921306610107},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.06743815541267395},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3606368","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3606368","pdf_url":null,"source":{"id":"https://openalex.org/S4394735545","display_name":"ACM Transactions on Information Systems","issn_l":"1046-8188","issn":["1046-8188","1558-2868"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Information Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6499999761581421,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G3881774828","display_name":null,"funder_award_id":"ZR2022YQ59","funder_id":"https://openalex.org/F4320324174","funder_display_name":"Natural Science Foundation of Shandong Province"},{"id":"https://openalex.org/G7231895066","display_name":null,"funder_award_id":"U1936203","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324174","display_name":"Natural Science Foundation of Shandong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1991927948","https://openalex.org/W2250539671","https://openalex.org/W2524182563","https://openalex.org/W2593831809","https://openalex.org/W2897182555","https://openalex.org/W2914393402","https://openalex.org/W2980540750","https://openalex.org/W2981852735","https://openalex.org/W3010548497","https://openalex.org/W3034999214","https://openalex.org/W3042061728","https://openalex.org/W3047616836","https://openalex.org/W3090325439","https://openalex.org/W3135644062","https://openalex.org/W3153421894","https://openalex.org/W3160936529","https://openalex.org/W3195014936","https://openalex.org/W3196691777","https://openalex.org/W3207707577","https://openalex.org/W3209028787","https://openalex.org/W3214192224","https://openalex.org/W4205231570","https://openalex.org/W4221103197","https://openalex.org/W4225769560","https://openalex.org/W4226139158","https://openalex.org/W4286663339","https://openalex.org/W4288089799","https://openalex.org/W4312409772","https://openalex.org/W4312974570","https://openalex.org/W4392366624","https://openalex.org/W6763093128"],"related_works":["https://openalex.org/W48079147","https://openalex.org/W2394821827","https://openalex.org/W2563921006","https://openalex.org/W1963944933","https://openalex.org/W1600043506","https://openalex.org/W2111550420","https://openalex.org/W2549666521","https://openalex.org/W3133893348","https://openalex.org/W1977846844","https://openalex.org/W2901575119"],"abstract_inverted_index":{"Text":[0],"response":[1,15,91,154,180],"generation":[2,92,155],"for":[3,69,171],"multimodal":[4,18,70,134],"task-oriented":[5,71],"dialog":[6,72],"systems,":[7],"which":[8],"aims":[9,102],"to":[10,103,109,176],"generate":[11],"the":[12,17,42,50,97,105,116,120,129,133,144,152,174,178,189,192],"proper":[13],"text":[14,179],"given":[16,117],"context,":[19],"is":[20,148,169],"an":[21,163],"essential":[22],"yet":[23],"challenging":[24],"task.":[25],"Although":[26],"existing":[27],"efforts":[28],"have":[29],"achieved":[30],"compelling":[31],"success,":[32],"they":[33],"still":[34],"suffer":[35],"from":[36,137],"two":[37],"pivotal":[38],"limitations:":[39],"(1)":[40],"overlook":[41],"benefit":[43],"of":[44,76,115,191],"generative":[45,65],"pretraining":[46],"and":[47,89,112,140],"(2)":[48],"ignore":[49],"textual":[51,111],"context-related":[52],"knowledge":[53,81,99,107,131,175],".":[54,93],"To":[55,94],"address":[56],"these":[57],"limitations,":[58],"we":[59],"propose":[60],"a":[61,158,185],"novel":[62],"dual":[63,80,84,98,121],"knowledge-enhanced":[64,85,90,122,153],"pretrained":[66],"language":[67],"mode":[68],"systems":[73],"(DKMD),":[74],"consisting":[75],"three":[77],"key":[78],"components:":[79],"selection":[82,100],",":[83,88],"context":[86,123,135],"learning":[87,124,136],"be":[95],"specific,":[96],"component":[101,125,156],"select":[104],"related":[106],"according":[108],"both":[110,138],"visual":[113],"modalities":[114],"context.":[118],"Thereafter,":[119],"targets":[126],"seamlessly,":[127],"integrating":[128],"selected":[130],"into":[132],"global":[139],"local":[141],"perspectives,":[142],"where":[143,162],"cross-modal":[145],"semantic":[146],"relation":[147],"also":[149],"explored.":[150],"Moreover,":[151],"comprises":[157],"revised":[159],"BART":[160],"decoder,":[161],"additional":[164],"dot-product":[165],"knowledge-decoder":[166],"attention":[167],"sub-layer":[168],"introduced":[170],"explicitly":[172],"utilizing":[173],"advance":[177],"generation.":[181],"Extensive":[182],"experiments":[183],"on":[184],"public":[186],"dataset":[187],"verify":[188],"superiority":[190],"proposed":[193],"DKMD":[194],"over":[195],"state-of-the-art":[196],"competitors.":[197]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":5},{"year":2022,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}