{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T23:59:56Z","timestamp":1778889596467,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":44,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,10,17]],"date-time":"2021-10-17T00:00:00Z","timestamp":1634428800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Shandong Provincial Natural Science Foundation","award":["ZR2019JQ23"],"award-info":[{"award-number":["ZR2019JQ23"]}]},{"name":"Young creative team in universities of Shandong Province","award":["2020KJN012"],"award-info":[{"award-number":["2020KJN012"]}]},{"name":"Shandong Provincial Key Research and Development Program","award":["2019JZZY010118"],"award-info":[{"award-number":["2019JZZY010118"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62006142,61872270"],"award-info":[{"award-number":["62006142,61872270"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Kuaishou"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,10,17]]},"DOI":"10.1145\/3474085.3475234","type":"proceedings-article","created":{"date-parts":[[2021,10,18]],"date-time":"2021-10-18T20:56:12Z","timestamp":1634590572000},"page":"695-703","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":30,"title":["Multimodal Dialog System: Relational Graph-based Context-aware Question Understanding"],"prefix":"10.1145","author":[{"given":"Haoyu","family":"Zhang","sequence":"first","affiliation":[{"name":"Shandong University, Qingdao, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meng","family":"Liu","sequence":"additional","affiliation":[{"name":"Shandong Jianzhu University, Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zan","family":"Gao","sequence":"additional","affiliation":[{"name":"Shandong Artificial Intelligence Institute, Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoqiang","family":"Lei","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yinglong","family":"Wang","sequence":"additional","affiliation":[{"name":"Shandong Artificial Intelligence Institute, Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liqiang","family":"Nie","sequence":"additional","affiliation":[{"name":"Shandong University, Qingdao, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,10,17]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"The International Conference on Learning Representations. 1--15","author":"Diederik","unstructured":"Diederik P. Kingma andJimmy Ba. 2015. Adam: A method for stochastic optimization . In The International Conference on Learning Representations. 1--15 . Diederik P. Kingma andJimmy Ba. 2015. Adam: A method for stochastic optimization. In The International Conference on Learning Representations. 1--15."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1540"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3166054.3166058"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1189"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3209997"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331226"},{"key":"e_1_3_2_2_7_1","volume-title":"Proceedings of the Annual Meeting of the Association for Computational. 484--495","author":"Dhingra Bhuwan","year":"2016","unstructured":"Bhuwan Dhingra , Lihong Li , Xiujun Li , Jianfeng Gao , Yun-Nung Chen , Faisal Ahmed , and Li Deng . 2016 . Towards end-to-end reinforcement learning of dialogue agents for information access . In Proceedings of the Annual Meeting of the Association for Computational. 484--495 . Bhuwan Dhingra, Lihong Li, Xiujun Li, Jianfeng Gao, Yun-Nung Chen, Faisal Ahmed, and Li Deng. 2016. Towards end-to-end reinforcement learning of dialogue agents for information access. In Proceedings of the Annual Meeting of the Association for Computational. 484--495."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.5555\/1289189.1289273"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6280"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401054"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.54"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413679"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383123"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1127"},{"key":"e_1_3_2_2_16_1","volume-title":"Proceedings of the International Joint Conference on Natural Language Processing. 733--743","author":"Li Xiujun","year":"2017","unstructured":"Xiujun Li , Yun-Nung Chen , Lihong Li , Jianfeng Gao , and Asli Celikyilmaz . 2017 . End-to-end task-completion neural dialogue systems . In Proceedings of the International Joint Conference on Natural Language Processing. 733--743 . Xiujun Li, Yun-Nung Chen, Lihong Li, Jianfeng Gao, and Asli Celikyilmaz. 2017. End-to-end task-completion neural dialogue systems. In Proceedings of the International Joint Conference on Natural Language Processing. 733--743."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240646"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240605"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401250"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2875363"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240549"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350923"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"e_1_3_2_2_25_1","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence. 696--704","author":"Saha Amrita","year":"2018","unstructured":"Amrita Saha , Mitesh Khapra , and Karthik Sankaranarayanan . 2018 . Towards building large scale multimodal domain-aware conversation systems . In Proceedings of the AAAI Conference on Artificial Intelligence. 696--704 . Amrita Saha, Mitesh Khapra, and Karthik Sankaranarayanan. 2018. Towards building large scale multimodal domain-aware conversation systems. In Proceedings of the AAAI Conference on Artificial Intelligence. 696--704."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-1152"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123314"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210002"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401290"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"e_1_3_2_2_31_1","volume-title":"International Conference on Learning Representations. 1--12","author":"Cucurull Guillem","year":"2018","unstructured":"Guillem Cucurull , Arantxa Casanova , Adriana Romero , Pietro Lio , and Yoshua Bengio . 2018 . Graph attention networks . In International Conference on Learning Representations. 1--12 . Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, and Yoshua Bengio. 2018. Graph attention networks. In International Conference on Learning Representations. 1--12."},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.5555\/3016387.3016435"},{"key":"e_1_3_2_2_33_1","volume-title":"Proceedings of the International Conference on Computational Linguistics. 4100--4110","author":"Wang Jian","year":"2020","unstructured":"Jian Wang , Junhao Liu , Wei Bi , Xiaojiang Liu , Kejing He , Ruifeng Xu , and Min Yang . 2020 . Dual dynamic memory network for end-to-end multi-turn taskoriented dialog systems . In Proceedings of the International Conference on Computational Linguistics. 4100--4110 . Jian Wang, Junhao Liu, Wei Bi, Xiaojiang Liu, Kejing He, Ruifeng Xu, and Min Yang. 2020. Dual dynamic memory network for end-to-end multi-turn taskoriented dialog systems. In Proceedings of the International Conference on Computational Linguistics. 4100--4110."},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210061"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2923608"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351034"},{"key":"e_1_3_2_2_37_1","volume-title":"Proceedings of the Conference of the European Chapter of the Association for Computational Linguistics. 438--449","author":"Wen Tsung-Hsien","year":"2017","unstructured":"Tsung-Hsien Wen , David Vandyke , Lina M. Rojas- Barahona , Pei-Hao Su , Stefan Ultes , and Steve Young . 2017 . A network-based endto- end trainable task-oriented dialogue system . In Proceedings of the Conference of the European Chapter of the Association for Computational Linguistics. 438--449 . Tsung-Hsien Wen, David Vandyke, Lina M. Rojas- Barahona, Pei-Hao Su, Stefan Ultes, and Steve Young. 2017. A network-based endto- end trainable task-oriented dialogue system. In Proceedings of the Conference of the European Chapter of the Association for Computational Linguistics. 438--449."},{"key":"e_1_3_2_2_38_1","volume-title":"International Conference on Learning Representations. 1--15","author":"Weston Jason","year":"2015","unstructured":"Jason Weston , Sumit Chopra , and Antoine Bordes . 2015 . Memory networks . In International Conference on Learning Representations. 1--15 . Jason Weston, Sumit Chopra, and Antoine Bordes. 2015. Memory networks. In International Conference on Learning Representations. 1--15."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1046"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.5555\/3298023.3298055"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/2911451.2911542"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080843"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210011"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6507"}],"event":{"name":"MM '21: ACM Multimedia Conference","location":"Virtual Event China","acronym":"MM '21","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 29th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3474085.3475234","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3474085.3475234","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:48:16Z","timestamp":1750193296000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3474085.3475234"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,17]]},"references-count":44,"alternative-id":["10.1145\/3474085.3475234","10.1145\/3474085"],"URL":"https:\/\/doi.org\/10.1145\/3474085.3475234","relation":{},"subject":[],"published":{"date-parts":[[2021,10,17]]},"assertion":[{"value":"2021-10-17","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}