{"id":"https://openalex.org/W3192484213","doi":"https://doi.org/10.24963/ijcai.2021/548","title":"UniMF: A Unified Framework to Incorporate Multimodal Knowledge Bases intoEnd-to-End Task-Oriented Dialogue Systems","display_name":"UniMF: A Unified Framework to Incorporate Multimodal Knowledge Bases intoEnd-to-End Task-Oriented Dialogue Systems","publication_year":2021,"publication_date":"2021-08-01","ids":{"openalex":"https://openalex.org/W3192484213","doi":"https://doi.org/10.24963/ijcai.2021/548","mag":"3192484213"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2021/548","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/548","pdf_url":"https://www.ijcai.org/proceedings/2021/0548.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2021/0548.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110259784","display_name":"Shiquan Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Shiquan Yang","raw_affiliation_strings":["The University of Melbourne","The University of Melbourne, Australia"],"affiliations":[{"raw_affiliation_string":"The University of Melbourne","institution_ids":["https://openalex.org/I165779595"]},{"raw_affiliation_string":"The University of Melbourne, Australia","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100422092","display_name":"Rui Zhang","orcid":"https://orcid.org/0000-0002-8132-6250"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Zhang","raw_affiliation_strings":["Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070030398","display_name":"Sarah Erfani","orcid":"https://orcid.org/0000-0003-0885-0643"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Sarah M. Erfani","raw_affiliation_strings":["The University of Melbourne","The University of Melbourne, Australia"],"affiliations":[{"raw_affiliation_string":"The University of Melbourne","institution_ids":["https://openalex.org/I165779595"]},{"raw_affiliation_string":"The University of Melbourne, Australia","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032767467","display_name":"Jey Han Lau","orcid":"https://orcid.org/0000-0002-1647-4628"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jey Han Lau","raw_affiliation_strings":["The University of Melbourne","The University of Melbourne, Australia"],"affiliations":[{"raw_affiliation_string":"The University of Melbourne","institution_ids":["https://openalex.org/I165779595"]},{"raw_affiliation_string":"The University of Melbourne, Australia","institution_ids":["https://openalex.org/I165779595"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5110259784"],"corresponding_institution_ids":["https://openalex.org/I165779595"],"apc_list":null,"apc_paid":null,"fwci":2.0395,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.89054694,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3978","last_page":"3984"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9994000196456909,"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":0.9994000196456909,"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/T12031","display_name":"Speech and dialogue systems","score":0.9977999925613403,"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":0.9968000054359436,"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/computer-science","display_name":"Computer science","score":0.8525611162185669},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.640925407409668},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6085540652275085},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5609865188598633},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.4926486611366272},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4907034635543823},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4715433418750763},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4601081311702728},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3421732485294342},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12839025259017944},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.07833284139633179}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8525611162185669},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.640925407409668},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6085540652275085},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5609865188598633},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.4926486611366272},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4907034635543823},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4715433418750763},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4601081311702728},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3421732485294342},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12839025259017944},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.07833284139633179},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2021/548","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/548","pdf_url":"https://www.ijcai.org/proceedings/2021/0548.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2021/548","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/548","pdf_url":"https://www.ijcai.org/proceedings/2021/0548.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3192484213.pdf","grobid_xml":"https://content.openalex.org/works/W3192484213.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2558809543","https://openalex.org/W2583186419","https://openalex.org/W2798914047","https://openalex.org/W2945260553","https://openalex.org/W2951008357","https://openalex.org/W2962886331","https://openalex.org/W2963201498","https://openalex.org/W2963398599","https://openalex.org/W2963491014","https://openalex.org/W2963789888","https://openalex.org/W2964077278","https://openalex.org/W2965373594","https://openalex.org/W2980282514","https://openalex.org/W3034930293","https://openalex.org/W3035301094","https://openalex.org/W3117238912","https://openalex.org/W4295249402"],"related_works":["https://openalex.org/W2931688134","https://openalex.org/W2377919138","https://openalex.org/W2378857091","https://openalex.org/W4256502920","https://openalex.org/W103652678","https://openalex.org/W4226090359","https://openalex.org/W2020521331","https://openalex.org/W101162712","https://openalex.org/W4256618828","https://openalex.org/W2786691313"],"abstract_inverted_index":{"Knowledge":[0],"bases":[1,21,32,43],"(KBs)":[2],"are":[3],"usually":[4],"essential":[5],"for":[6],"building":[7],"practical":[8],"dialogue":[9,23,65,74,112,128],"systems.":[10,24,66],"Recently":[11],"we":[12,70,122],"have":[13],"seen":[14],"rapidly":[15],"growing":[16],"interest":[17],"in":[18,110],"integrating":[19],"knowledge":[20,31,42],"into":[22],"However,":[25],"existing":[26,58],"approaches":[27,59],"mostly":[28],"deal":[29],"with":[30,46,91],"of":[33,57,64,118,146],"a":[34,82,101,124],"single":[35],"modality,":[36],"typically":[37],"textual":[38],"information.":[39],"As":[40],"today's":[41],"become":[44],"abundant":[45],"multimodal":[47,88,133],"information":[48],"such":[49],"as":[50],"images,":[51],"audios":[52],"and":[53,76,137],"videos,":[54],"the":[55,62,98,111,116,119,144],"limitation":[56,79],"greatly":[60],"hinders":[61],"development":[63],"In":[67],"this":[68,78],"paper,":[69],"focus":[71],"on":[72,141],"task-oriented":[73],"systems":[75],"address":[77],"by":[80],"proposing":[81],"novel":[83,102],"model":[84,99],"that":[85],"integrates":[86],"external":[87],"KB":[89],"reasoning":[90],"pre-trained":[92],"language":[93],"models.":[94],"We":[95],"further":[96],"enhance":[97],"via":[100],"multi-granularity":[103],"fusion":[104],"mechanism":[105],"to":[106],"capture":[107],"multi-grained":[108],"semantics":[109],"history.":[113],"To":[114],"validate":[115],"effectiveness":[117],"proposed":[120,148],"model,":[121],"collect":[123],"new":[125],"large-scale":[126],"(14K)":[127],"dataset":[129],"MMDialKB,":[130],"built":[131],"upon":[132],"KB.":[134],"Both":[135],"automatic":[136],"human":[138],"evaluation":[139],"results":[140],"MMDialKB":[142],"demonstrate":[143],"superiority":[145],"our":[147],"framework":[149],"over":[150],"strong":[151],"baselines.":[152]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}