{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T15:53:52Z","timestamp":1761062032329,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":28,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819608461"},{"type":"electronic","value":"9789819608478"}],"license":[{"start":{"date-parts":[[2024,12,14]],"date-time":"2024-12-14T00:00:00Z","timestamp":1734134400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,14]],"date-time":"2024-12-14T00:00:00Z","timestamp":1734134400000},"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":[[2025]]},"DOI":"10.1007\/978-981-96-0847-8_6","type":"book-chapter","created":{"date-parts":[[2024,12,13]],"date-time":"2024-12-13T04:26:47Z","timestamp":1734064007000},"page":"79-93","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Emergency Entity and Relationship Extraction Based on a Multimodal Deep Learning Method"],"prefix":"10.1007","author":[{"given":"Peng","family":"Wu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"Ni","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,14]]},"reference":[{"key":"6_CR1","doi-asserted-by":"crossref","unstructured":"Wu, Z., Zheng, C., Cai, Y., Chen, J., Leung, H.-F., Li, Q.: Multimodal representation with embedded visual guiding objects for named entity recognition in social media posts. In: ACM MM, pp. 1038\u20131046 (2020)","DOI":"10.1145\/3394171.3413650"},{"key":"6_CR2","doi-asserted-by":"crossref","unstructured":"Moon, S., Neves, L., Carvalho, V.: Multimodal named entity recognition for short social media posts. In: NAACL-HLT, pp. 852\u2013860 (2018)","DOI":"10.18653\/v1\/N18-1078"},{"key":"6_CR3","doi-asserted-by":"crossref","unstructured":"Xu, B., Huang, S., Sha, C., Wang, H.: MAF: a general matching and alignment framework for multimodal named entity recognition. In: WSDM, pp. 1215\u20131223 (2022)","DOI":"10.1145\/3488560.3498475"},{"key":"6_CR4","doi-asserted-by":"crossref","unstructured":"Chen, X., et al.: Good visual guidance make a better extractor: hierarchical visual prefix for multimodal entity and relation extraction. In: NAACL, pp. 1607\u20131618 (2022)","DOI":"10.18653\/v1\/2022.findings-naacl.121"},{"key":"6_CR5","first-page":"9694","volume":"34","author":"J Li","year":"2021","unstructured":"Li, J., Selvaraju, R., Gotmare, A., Joty, S., Xiong, C., Hoi, S.C.H.: Align before fuse: vision and language representation learning with momentum distillation. Adv. Neural. Inf. Process. Syst. 34, 9694\u20139705 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"6_CR6","unstructured":"Devlin, J., Chang, M.-W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv:1810.04805 (2018)"},{"key":"6_CR7","doi-asserted-by":"crossref","unstructured":"Zhong, Z., Chen, D.: A frustratingly easy approach for entity and relation extraction. In: NAACL-HLT, pp. 50\u201361 (2021)","DOI":"10.18653\/v1\/2021.naacl-main.5"},{"key":"6_CR8","doi-asserted-by":"crossref","unstructured":"Li, G., Duan, N., Fang, Y., Gong, M., Jiang, D.: Unicoder-vl: a universal encoder for vision and language by cross-modal pre-training. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 11336\u201311344 (2020)","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"6_CR9","unstructured":"Li, J., Zhou, P., Xiong, C., Hoi, S.: Prototypical Contrastive Learning of Unsupervised Representations. arXiv: 2005.04966 (2020)"},{"key":"6_CR10","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: ICML, pp. 1597\u20131607 (2020)"},{"key":"6_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: CVPR, pp. 9729\u20139738 (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"6_CR12","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML, pp. 8748\u20138763 (2021)"},{"key":"6_CR13","unstructured":"Dosovitskiy, A., et al.: An image is worth 16\u00d716 words: transformers for image recognition at scale. arXiv:2010.11929 (2020)"},{"key":"6_CR14","doi-asserted-by":"crossref","unstructured":"Zhang, Q., Fu, J., Liu, X., Huang, X.: Adaptive co-attention network for named entity recognition in tweets. In: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 32, No. 1 (2018)","DOI":"10.1609\/aaai.v32i1.11962"},{"key":"6_CR15","doi-asserted-by":"crossref","unstructured":"Zhang, D., Wei, S., Li, S., Wu, H., Zhu, Q., Zhou, G.: Multi-modal graph fusion for named entity recognition with targeted visual guidance. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 14347\u201314355 (2021)","DOI":"10.1609\/aaai.v35i16.17687"},{"key":"6_CR16","doi-asserted-by":"crossref","unstructured":"Li, J., et al.: Prompting chatgpt in MNER: enhanced multimodal named entity recognition with auxiliary refined knowledge. In: EMNLP, pp. 2787\u20132802 (2023)","DOI":"10.18653\/v1\/2023.findings-emnlp.184"},{"key":"6_CR17","unstructured":"Xu, B., et al.: Different data, different modalities! Reinforced data splitting for effective multimodal information extraction from social media posts. In: COLING, pp. 1855\u20131864 (2022)"},{"key":"6_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.124867","volume":"255","author":"Q Zeng","year":"2024","unstructured":"Zeng, Q., Yuan, M., Wan, J., et al.: ICKA: an instruction construction and knowledge alignment framework for multimodal named entity recognition. Expert Syst. Appl. 255, 124867 (2024)","journal-title":"Expert Syst. Appl."},{"key":"6_CR19","doi-asserted-by":"crossref","unstructured":"Zheng, C., Feng, J., Fu, Z., Cai, Y., Li, Q., Wang, T.: Multimodal relation extraction with efficient graph alignment. In: ACM MM, pp. 5298\u20135306 (2021)","DOI":"10.1145\/3474085.3476968"},{"key":"6_CR20","doi-asserted-by":"crossref","unstructured":"Yuan, L., Cai, Y., Wang, J., Li, Q.: Joint multimodal entity-relation extraction based on edge-enhanced graph alignment network and word-pair relation tagging. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 11051\u201311059 (2023)","DOI":"10.1609\/aaai.v37i9.26309"},{"key":"6_CR21","doi-asserted-by":"crossref","unstructured":"Chen X, et al.: Good visual guidance makes a better extractor: hierarchical visual prefix for multimodal entity and relation extraction. arXiv:220503521 (2022)","DOI":"10.18653\/v1\/2022.findings-naacl.121"},{"issue":"3","key":"6_CR22","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1016\/j.ipm.2023.103264","volume":"60","author":"Q Zhao","year":"2023","unstructured":"Zhao, Q., Gao, T., Guo, N.: TSVFN: two-stage visual fusion network for multimodal relation extraction. Inf. Process. Manage. 60(3), 17 (2023)","journal-title":"Inf. Process. Manage."},{"key":"6_CR23","doi-asserted-by":"publisher","first-page":"1274","DOI":"10.1109\/TASLP.2023.3345146","volume":"32","author":"S Cui","year":"2024","unstructured":"Cui, S., Cao, J., Cong, X., et al.: Enhancing multimodal entity and relation extraction with variational information bottleneck. IEEE\/ACM Trans. Audio Speech Lang. Process. 32, 1274\u20131285 (2024)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"6_CR24","doi-asserted-by":"crossref","unstructured":"Yu, J., Jiang, J., Yang, L., Xia, R.: Improving multimodal named entity recognition via entity span detection with unified multimodal transformer. In: ACL, pp. 3342\u20133352 (2020)","DOI":"10.18653\/v1\/2020.acl-main.306"},{"key":"6_CR25","doi-asserted-by":"crossref","unstructured":"Lu, D., Neves, L., Carvalho, V., Zhang, N., Ji, H.: Visual attention model for name tagging in multimodal social media. In: ACL, pp. 1990\u20131999 (2018)","DOI":"10.18653\/v1\/P18-1185"},{"key":"6_CR26","doi-asserted-by":"crossref","unstructured":"Zheng, C., Wu, Z., Feng, J., Fu, Z., Cai, Y.: Mnre: a challenge multimodal dataset for neural relation extraction with visual evidence in social media posts. In: ICME, pp. 1\u20136 (2021)","DOI":"10.1109\/ICME51207.2021.9428274"},{"key":"6_CR27","doi-asserted-by":"crossref","unstructured":"Sun, L., Wang, J., Zhang, K., Su, Y., Weng, F.: RpBERT: a text-image relation propagation-based BERT model for multimodal NER. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 13860\u201313868 (2021)","DOI":"10.1609\/aaai.v35i15.17633"},{"key":"6_CR28","doi-asserted-by":"crossref","unstructured":"Wei, Z., Su, J., Wang, Y., Tian, Y., Chang, Y.: A novel cascade binary tagging framework for relational triple extraction. In: ACL, pp. 1476\u20131488 (2020)","DOI":"10.18653\/v1\/2020.acl-main.136"}],"container-title":["Lecture Notes in Computer Science","Advanced Data Mining and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-0847-8_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,13]],"date-time":"2024-12-13T05:03:55Z","timestamp":1734066235000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-0847-8_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,14]]},"ISBN":["9789819608461","9789819608478"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-0847-8_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,14]]},"assertion":[{"value":"14 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ADMA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Advanced Data Mining and Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sydney, NSW","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"adma2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/adma2024.github.io\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}