{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T19:45:53Z","timestamp":1743018353692,"version":"3.40.3"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031446986"},{"type":"electronic","value":"9783031446993"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-44699-3_36","type":"book-chapter","created":{"date-parts":[[2023,10,7]],"date-time":"2023-10-07T08:02:39Z","timestamp":1696665759000},"page":"399-411","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Multimodal Dialogue Understanding via\u00a0Holistic Modeling and\u00a0Sequence Labeling"],"prefix":"10.1007","author":[{"given":"Chenran","family":"Cai","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qin","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruifeng","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bing","family":"Qin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,10,8]]},"reference":[{"key":"36_CR1","doi-asserted-by":"crossref","unstructured":"Alamri, H., et al.: Audio visual scene-aware dialog. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7558\u20137567 (2019)","DOI":"10.1109\/CVPR.2019.00774"},{"key":"36_CR2","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1007\/s10458-008-9074-5","volume":"19","author":"E Black","year":"2009","unstructured":"Black, E., Hunter, A.: An inquiry dialogue system. Auton. Agent. Multi-Agent Syst. 19, 173\u2013209 (2009)","journal-title":"Auton. Agent. Multi-Agent Syst."},{"key":"36_CR3","doi-asserted-by":"crossref","unstructured":"Cai, D., Wang, Y., Liu, L., Shi, S.: Recent advances in retrieval-augmented text generation. In: Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 3417\u20133419 (2022)","DOI":"10.1145\/3477495.3532682"},{"key":"36_CR4","unstructured":"Dosovitskiy, A., et al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. In: International Conference on Learning Representations"},{"key":"36_CR5","doi-asserted-by":"crossref","unstructured":"Fang, Y., et al.: From spoken dialogue to formal summary: an utterance rewriting for dialogue summarization. In: Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 3859\u20133869 (2022)","DOI":"10.18653\/v1\/2022.naacl-main.283"},{"key":"36_CR6","doi-asserted-by":"crossref","unstructured":"Galley, M., McKeown, K., Fosler-Lussier, E., Jing, H.: Discourse segmentation of multi-party conversation. In: Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics, pp. 562\u2013569 (2003)","DOI":"10.3115\/1075096.1075167"},{"key":"36_CR7","doi-asserted-by":"publisher","first-page":"2765","DOI":"10.1007\/s00521-021-06748-3","volume":"34","author":"T Hao","year":"2021","unstructured":"Hao, T., Li, X., He, Y., Wang, F.L., Qu, Y.: Recent progress in leveraging deep learning methods for question answering. Neural Comput. Appl. 34, 2765\u20132783 (2021). https:\/\/doi.org\/10.1007\/s00521-021-06748-3","journal-title":"Neural Comput. Appl."},{"key":"36_CR8","unstructured":"He, P., Liu, X., Gao, J., Chen, W.: DeBERTa: Decoding-enhanced BERT with disentangled attention. In: International Conference on Learning Representations"},{"key":"36_CR9","doi-asserted-by":"crossref","unstructured":"He, W., et al.: Unified dialog model pre-training for task-oriented dialog understanding and generation. In: Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 187\u2013200 (2022)","DOI":"10.1145\/3477495.3532069"},{"key":"36_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"709","DOI":"10.1007\/978-3-030-58548-8_41","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Q Huang","year":"2020","unstructured":"Huang, Q., Xiong, Yu., Rao, A., Wang, J., Lin, D.: MovieNet: a Holistic Dataset for Movie Understanding. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12349, pp. 709\u2013727. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58548-8_41"},{"key":"36_CR11","doi-asserted-by":"crossref","unstructured":"Khan, O.Z., Robichaud, J.P., Crook, P.A., Sarikaya, R.: Hypotheses ranking and state tracking for a multi-domain dialog system using multiple ASR alternates. In: Sixteenth Annual Conference of the International Speech Communication Association (2015)","DOI":"10.21437\/Interspeech.2015-459"},{"key":"36_CR12","doi-asserted-by":"publisher","first-page":"453","DOI":"10.1162\/tacl_a_00276","volume":"7","author":"T Kwiatkowski","year":"2019","unstructured":"Kwiatkowski, T., et al.: Natural questions: a benchmark for question answering research. Trans. Assoc. Comput. Linguist. 7, 453\u2013466 (2019)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"36_CR13","doi-asserted-by":"crossref","unstructured":"Liao, L., Ma, Y., He, X., Hong, R., Chua, T.S.: Knowledge-aware multimodal dialogue systems. In: Proceedings of the 26th ACM International Conference on Multimedia, pp. 801\u2013809 (2018)","DOI":"10.1145\/3240508.3240605"},{"key":"36_CR14","doi-asserted-by":"crossref","unstructured":"Rao, A., et al.: A local-to-global approach to multi-modal movie scene segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10146\u201310155 (2020)","DOI":"10.1109\/CVPR42600.2020.01016"},{"key":"36_CR15","doi-asserted-by":"crossref","unstructured":"Seltzer, J., Cheng, K., Zong, S., Lin, J.: Flipping the script: inverse information seeking dialogues for market research. In: Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 3380\u20133383 (2022)","DOI":"10.1145\/3477495.3536326"},{"issue":"8","key":"36_CR16","doi-asserted-by":"publisher","first-page":"1163","DOI":"10.1109\/TCSVT.2011.2138830","volume":"21","author":"P Sidiropoulos","year":"2011","unstructured":"Sidiropoulos, P., Mezaris, V., Kompatsiaris, I., Meinedo, H., Bugalho, M., Trancoso, I.: Temporal video segmentation to scenes using high-level audiovisual features. IEEE Trans. Circ. Syst. Video Technol. 21(8), 1163\u20131177 (2011)","journal-title":"IEEE Trans. Circ. Syst. Video Technol."},{"key":"36_CR17","unstructured":"Su, J., Lu, Y., Pan, S., Wen, B., Liu, Y.: RoFormer: enhanced transformer with rotary position embedding (2021)"},{"key":"36_CR18","unstructured":"Sun, Y., et al.: ERNIE 3.0: large-scale knowledge enhanced pre-training for language understanding and generation. arXiv preprint arXiv:2107.02137 (2021)"},{"key":"36_CR19","doi-asserted-by":"crossref","unstructured":"Takanobu, R., et al.: A weakly supervised method for topic segmentation and labeling in goal-oriented dialogues via reinforcement learning. In: IJCAI, pp. 4403\u20134410 (2018)","DOI":"10.24963\/ijcai.2018\/612"},{"key":"36_CR20","doi-asserted-by":"crossref","unstructured":"Valizadeh, M., Parde, N.: The AI doctor is. In: A survey of task-oriented dialogue systems for healthcare applications. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 6638\u20136660 (2022)","DOI":"10.18653\/v1\/2022.acl-long.458"},{"key":"36_CR21","doi-asserted-by":"publisher","unstructured":"Wang, Y., Zhao, X., Zhao, D.: Overview of the NLPCC 2022 shared task: multi-modal dialogue understanding and generation. In: In: Lu, W., Huang, S., Hong, Y., Zhou, X. (eds.) Natural Language Processing and Chinese Computing: 11th CCF International Conference, NLPCC 2022, Guilin, China, September 24\u201325, 2022, Proceedings, Part II, vol. 13552, pp. 328\u2013335. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-17189-5_29","DOI":"10.1007\/978-3-031-17189-5_29"},{"key":"36_CR22","doi-asserted-by":"crossref","unstructured":"Wu, H., Xu, K., Song, L., Jin, L., Zhang, H., Song, L.: Domain-adaptive pretraining methods for dialogue understanding. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pp. 665\u2013669. Association for Computational Linguistics, Online (Aug 2021)","DOI":"10.18653\/v1\/2021.acl-short.84"},{"key":"36_CR23","doi-asserted-by":"crossref","unstructured":"Wu, H., et al.: Scene consistency representation learning for video scene segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14021\u201314030 (2022)","DOI":"10.1109\/CVPR52688.2022.01363"},{"key":"36_CR24","doi-asserted-by":"crossref","unstructured":"Xia, J., et al.: Dialogue topic segmentation via parallel extraction network with neighbor smoothing. In: Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 2126\u20132131 (2022)","DOI":"10.1145\/3477495.3531817"},{"key":"36_CR25","doi-asserted-by":"crossref","unstructured":"Xing, L., Carenini, G.: Improving unsupervised dialogue topic segmentation with utterance-pair coherence scoring. arXiv preprint arXiv:2106.06719 (2021)","DOI":"10.18653\/v1\/2021.sigdial-1.18"},{"key":"36_CR26","doi-asserted-by":"crossref","unstructured":"Xu, Y., Zhao, H., Zhang, Z.: Topic-aware multi-turn dialogue modeling. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 14176\u201314184 (2021)","DOI":"10.1609\/aaai.v35i16.17668"},{"key":"36_CR27","doi-asserted-by":"crossref","unstructured":"Zhang, H., Liu, M., Gao, Z., Lei, X., Wang, Y., Nie, L.: Multimodal dialog system: relational graph-based context-aware question understanding. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 695\u2013703 (2021)","DOI":"10.1145\/3474085.3475234"},{"key":"36_CR28","unstructured":"Zhang, J., et al: Fengshenbang 1.0: Being the foundation of Chinese cognitive intelligence (2023)"}],"container-title":["Lecture Notes in Computer Science","Natural Language Processing and Chinese Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-44699-3_36","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,23]],"date-time":"2023-12-23T13:57:29Z","timestamp":1703339849000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-44699-3_36"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031446986","9783031446993"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-44699-3_36","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"8 October 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"NLPCC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"CCF International Conference on Natural Language Processing and Chinese Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Foshan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"nlpcc2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/tcci.ccf.org.cn\/conference\/2023\/index.php","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Softconf","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"478","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"143","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"30% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}