{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T00:50:25Z","timestamp":1743036625629,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":19,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819984282"},{"type":"electronic","value":"9789819984299"}],"license":[{"start":{"date-parts":[[2023,12,24]],"date-time":"2023-12-24T00:00:00Z","timestamp":1703376000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,12,24]],"date-time":"2023-12-24T00:00:00Z","timestamp":1703376000000},"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":[[2024]]},"DOI":"10.1007\/978-981-99-8429-9_31","type":"book-chapter","created":{"date-parts":[[2023,12,23]],"date-time":"2023-12-23T08:02:17Z","timestamp":1703318537000},"page":"383-394","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Discovering Multimodal Hierarchical Structures with\u00a0Graph Neural Networks for\u00a0Multi-modal and\u00a0Multi-hop Question Answering"],"prefix":"10.1007","author":[{"given":"Qing","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haocheng","family":"Lv","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiyun","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianyong","family":"Duan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingying","family":"Xv","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,12,24]]},"reference":[{"key":"31_CR1","doi-asserted-by":"crossref","unstructured":"Chang, Y., Narang, M., Suzuki, H., Cao, G., Gao, J., Bisk, Y.: WebQA: multihop and multimodal QA. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16495\u201316504 (2022)","DOI":"10.1109\/CVPR52688.2022.01600"},{"key":"31_CR2","doi-asserted-by":"crossref","unstructured":"Oguz, B., et al.: UniK-QA: unified representations of structured and unstructured knowledge for open-domain question answering. In: Findings of the Association for Computational Linguistics: NAACL 2022, pp. 1535\u20131546, July 2022","DOI":"10.18653\/v1\/2022.findings-naacl.115"},{"key":"31_CR3","doi-asserted-by":"crossref","unstructured":"Qi, P., Lee, H., Sido, T., Manning, C.D.: Answering open-domain questions of varying reasoning steps from text. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 3599\u20133614, November 2021","DOI":"10.18653\/v1\/2021.emnlp-main.292"},{"key":"31_CR4","unstructured":"Smith, D.A., Smith, N.A.: Probabilistic models of nonprojective dependency trees. In: Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL), pp. 132\u2013140, June 2007"},{"key":"31_CR5","unstructured":"Koo, T., Globerson, A., Carreras P\u00e9rez, X., Collins, M.: Structured prediction models via the matrix-tree theorem. In: Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL), pp. 141\u2013150 (2007)"},{"key":"31_CR6","doi-asserted-by":"crossref","unstructured":"McDonald, R., Satta, G.: On the complexity of non-projective data-driven dependency parsing. In: Proceedings of the Tenth International Conference on Parsing Technologies, pp. 121\u2013132, June 2007","DOI":"10.3115\/1621410.1621426"},{"key":"31_CR7","unstructured":"Talmor, A., et al.: MultiModalQA: complex question answering over text, tables and images (2021). arXiv preprint arXiv:2104.06039"},{"key":"31_CR8","doi-asserted-by":"crossref","unstructured":"Dhingra, B., Jin, Q., Yang, Z., Cohen, W., Salakhutdinov, R.: Neural models for reasoning over multiple mentions using coreference. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), pp. 42\u201348, June 2018","DOI":"10.18653\/v1\/N18-2007"},{"key":"31_CR9","doi-asserted-by":"crossref","unstructured":"Clark, C., Gardner, M.: Simple and effective multi-paragraph reading comprehension. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 845\u2013855, July 2018","DOI":"10.18653\/v1\/P18-1078"},{"key":"31_CR10","doi-asserted-by":"crossref","unstructured":"Tu, M., Wang, G., Huang, J., Tang, Y., He, X., Zhou, B.: Multi-hop reading comprehension across multiple documents by reasoning over heterogeneous graphs. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 2704\u20132713, July 2019","DOI":"10.18653\/v1\/P19-1260"},{"key":"31_CR11","doi-asserted-by":"crossref","unstructured":"Tang, Z., Shen, Y., Ma, X., Xu, W., Yu, J., Lu, W.: Multi-hop reading comprehension across documents with path-based graph convolutional network. In: Proceedings of the Twenty-Ninth International Conference on International Joint Conferences on Artificial Intelligence, pp. 3905\u20133911, January 2021","DOI":"10.24963\/ijcai.2020\/540"},{"key":"31_CR12","doi-asserted-by":"crossref","unstructured":"Kundu, S., Khot, T., Sabharwal, A., Clark, P.: Exploiting explicit paths for multi-hop reading comprehension. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 2737\u20132747, July 2019","DOI":"10.18653\/v1\/P19-1263"},{"key":"31_CR13","unstructured":"Chen, J., Lin, S., Durrett, G.: Multi-hop question answering via reasoning chains. arXiv preprint arXiv:1910.02610 (2019)"},{"key":"31_CR14","doi-asserted-by":"crossref","unstructured":"Min, S., Zhong, V., Zettlemoyer, L., Hajishirzi, H.: Multi-hop reading comprehension through question decomposition and rescoring. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 6097\u20136109, July 2019","DOI":"10.18653\/v1\/P19-1613"},{"key":"31_CR15","doi-asserted-by":"crossref","unstructured":"Wang, D., Liu, P., Zheng, Y., Qiu, X., Huang, X.J.: Heterogeneous graph neural networks for extractive document summarization. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 6209\u20136219, July 2020","DOI":"10.18653\/v1\/2020.acl-main.553"},{"key":"31_CR16","doi-asserted-by":"crossref","unstructured":"Jin, H., Wang, T., Wan, X.: SemSUM: semantic dependency guided neural abstractive summarization. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, no. 05, pp. 8026\u20138033, April 2020","DOI":"10.1609\/aaai.v34i05.6312"},{"key":"31_CR17","doi-asserted-by":"crossref","unstructured":"Qiu, Y., Cohen, S.B.: Abstractive summarization guided by latent hierarchical document structure. In: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pp. 5303\u20135317, December 2022","DOI":"10.18653\/v1\/2022.emnlp-main.355"},{"key":"31_CR18","doi-asserted-by":"crossref","unstructured":"Wang, W., Pan, S.: Deep inductive logic reasoning for multi-hop reading comprehension. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 4999\u20135009, May 2022","DOI":"10.18653\/v1\/2022.acl-long.343"},{"key":"31_CR19","doi-asserted-by":"crossref","unstructured":"Zhou, L., Palangi, H., Zhang, L., Hu, H., Corso, J., Gao, J.: Unified vision-language pre-training for image captioning and VQA. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, no. 07, pp. 13041\u201313049, April 2020","DOI":"10.1609\/aaai.v34i07.7005"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-8429-9_31","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,23]],"date-time":"2023-12-23T08:20:45Z","timestamp":1703319645000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-8429-9_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,24]]},"ISBN":["9789819984282","9789819984299"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-8429-9_31","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023,12,24]]},"assertion":[{"value":"24 December 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Xiamen","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":"13 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":"6","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/prcv2023.xmu.edu.cn\/","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":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1420","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":"532","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":"37% - 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":"3,78","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":"3,69","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)"}}]}}