{"id":"https://openalex.org/W3093418251","doi":"https://doi.org/10.1145/3394171.3413679","title":"Multimodal Dialogue Systems via Capturing Context-aware Dependencies of Semantic Elements","display_name":"Multimodal Dialogue Systems via Capturing Context-aware Dependencies of Semantic Elements","publication_year":2020,"publication_date":"2020-10-12","ids":{"openalex":"https://openalex.org/W3093418251","doi":"https://doi.org/10.1145/3394171.3413679","mag":"3093418251"},"language":"en","primary_location":{"id":"doi:10.1145/3394171.3413679","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3413679","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100724440","display_name":"Weidong He","orcid":"https://orcid.org/0000-0003-1986-9710"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weidong He","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100382306","display_name":"Zhi Li","orcid":"https://orcid.org/0000-0002-8061-7486"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhi Li","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035888909","display_name":"Dongcai Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongcai Lu","raw_affiliation_strings":["HUAWEI Technologies, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HUAWEI Technologies, Hangzhou, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048237545","display_name":"Enhong Chen","orcid":"https://orcid.org/0000-0002-4835-4102"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Enhong Chen","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025292786","display_name":"Tong Xu","orcid":"https://orcid.org/0000-0003-4246-5386"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tong Xu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020858666","display_name":"Baoxing Huai","orcid":"https://orcid.org/0000-0001-9625-2314"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baoxing Huai","raw_affiliation_strings":["HUAWEI Technologies, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HUAWEI Technologies, Hangzhou, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007552078","display_name":"Jing Yuan","orcid":"https://orcid.org/0000-0001-9178-3896"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Yuan","raw_affiliation_strings":["HUAWEI Technologies, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HUAWEI Technologies, Hangzhou, China","institution_ids":["https://openalex.org/I2250955327"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2755","last_page":"2764"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9994999766349792,"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/T10028","display_name":"Topic Modeling","score":0.9990000128746033,"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":0.8334980010986328},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6648297905921936},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6038583517074585},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5712329149246216},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5125484466552734},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5027461051940918},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.49087101221084595},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.48319709300994873},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.46704453229904175},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43427175283432007},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4183768630027771},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.35701894760131836}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8334980010986328},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6648297905921936},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6038583517074585},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5712329149246216},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5125484466552734},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5027461051940918},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.49087101221084595},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.48319709300994873},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.46704453229904175},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43427175283432007},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4183768630027771},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35701894760131836},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3394171.3413679","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3413679","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6299999952316284,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1902237438","https://openalex.org/W1933349210","https://openalex.org/W1975244201","https://openalex.org/W1975879668","https://openalex.org/W2016589492","https://openalex.org/W2078861931","https://openalex.org/W2095705004","https://openalex.org/W2157331557","https://openalex.org/W2194775991","https://openalex.org/W2296712013","https://openalex.org/W2339852062","https://openalex.org/W2752047430","https://openalex.org/W2798392716","https://openalex.org/W2798914047","https://openalex.org/W2891416139","https://openalex.org/W2897182555","https://openalex.org/W2897195437","https://openalex.org/W2949888546","https://openalex.org/W2951450739","https://openalex.org/W2951508633","https://openalex.org/W2956125353","https://openalex.org/W2963068985","https://openalex.org/W2963167310","https://openalex.org/W2963206148","https://openalex.org/W2963403868","https://openalex.org/W2963797754","https://openalex.org/W2963903950","https://openalex.org/W2964202354","https://openalex.org/W2965398302","https://openalex.org/W2981591098","https://openalex.org/W2994814507","https://openalex.org/W3034891407","https://openalex.org/W3035111931","https://openalex.org/W3101567279","https://openalex.org/W4247780151"],"related_works":["https://openalex.org/W2106922437","https://openalex.org/W2807901368","https://openalex.org/W2158491338","https://openalex.org/W2133733652","https://openalex.org/W2072658171","https://openalex.org/W2606392311","https://openalex.org/W4385956668","https://openalex.org/W2900895161","https://openalex.org/W4380838366","https://openalex.org/W2539884462"],"abstract_inverted_index":{"Recently,":[0],"multimodal":[1,42,95,143],"dialogue":[2,144],"systems":[3,84],"have":[4],"engaged":[5],"increasing":[6],"attention":[7],"in":[8,146],"several":[9],"domains":[10],"such":[11],"as":[12,69,71],"retail,":[13],"travel,":[14],"etc.":[15],"In":[16],"spite":[17],"of":[18,22,41,59,66,130],"the":[19,38,52,60,94,105,122,127,147,152],"promising":[20],"performance":[21],"pioneer":[23],"works,":[24],"existing":[25],"studies":[26],"usually":[27],"focus":[28],"on":[29,140],"utterance-level":[30],"semantic":[31,43,106],"representations":[32],"with":[33,85,163],"hierarchical":[34],"structures,":[35],"which":[36],"ignore":[37],"context-aware":[39],"dependencies":[40],"elements,":[44],"i.e.,":[45],"words":[46],"and":[47,97,125,150,157],"images.":[48],"Moreover,":[49],"when":[50],"integrating":[51],"visual":[53],"content,":[54],"they":[55],"only":[56],"consider":[57],"images":[58,116,131],"current":[61,123],"turn,":[62],"leaving":[63],"out":[64],"ones":[65],"previous":[67],"turns":[68],"well":[70],"their":[72],"ordinal":[73],"information.":[74],"To":[75],"address":[76],"these":[77],"issues,":[78],"we":[79,92,111,136],"propose":[80],"a":[81,99,141],"Multimodal":[82,100],"diAlogue":[83],"semanTic":[86],"Elements,":[87],"MATE":[88],"for":[89],"short.":[90],"Specifically,":[91],"unfold":[93],"inputs":[96],"devise":[98],"Element-level":[101],"Encoder":[102],"to":[103,121],"obtain":[104],"representation":[107],"at":[108],"element-level.":[109],"Besides,":[110],"take":[112],"into":[113],"consideration":[114],"all":[115],"that":[117],"might":[118],"be":[119],"relevant":[120],"turn":[124],"inject":[126],"sequential":[128],"characteristics":[129],"through":[132],"position":[133],"encoding.":[134],"Finally,":[135],"make":[137],"comprehensive":[138],"experiments":[139],"public":[142],"dataset":[145],"retail":[148],"domain,":[149],"improve":[151],"BLUE-4":[153],"score":[154,159],"by":[155,160],"9.49,":[156],"NIST":[158],"1.8469":[161],"compared":[162],"state-of-the-art":[164],"methods.":[165]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}