{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T04:27:04Z","timestamp":1780547224785,"version":"3.54.1"},"publisher-location":"Singapore","reference-count":37,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819756681","type":"print"},{"value":"9789819756698","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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\/978-981-97-5669-8_34","type":"book-chapter","created":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T17:02:31Z","timestamp":1722618151000},"page":"414-426","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Semantics Fusion of Hierarchical Transformers for Multimodal Named Entity Recognition"],"prefix":"10.1007","author":[{"given":"Zhao","family":"Tong","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haichao","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuwei","family":"Xia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shu","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiao-Yu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,8,3]]},"reference":[{"key":"34_CR1","unstructured":"Devlin, J., Chang, M.W., Lee, K., et al.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"34_CR2","doi-asserted-by":"crossref","unstructured":"Liu, C., Zhu, C., Zhu, W.: Chinese named entity recognition based on BERT with whole word masking. In: Proceedings of the 2020 6th International Conference on Computing and Artificial Intelligence, pp. 311\u2013316 (2020)","DOI":"10.1145\/3404555.3404563"},{"key":"34_CR3","doi-asserted-by":"crossref","unstructured":"Zhao, S., Hu, M., Cai, Z., et al.: Modeling dense cross-modal interactions for joint entity-relation extraction. In: Proceedings of the Twenty-Ninth International Conference on International Joint Conferences on Artificial Intelligence, pp. 4032\u20134038 (2021)","DOI":"10.24963\/ijcai.2020\/558"},{"key":"34_CR4","doi-asserted-by":"crossref","unstructured":"Lample, G., Ballesteros, M., Subramanian, S., et al.: Neural architectures for named entity recognition. arXiv preprint arXiv:1603.01360 (2016)","DOI":"10.18653\/v1\/N16-1030"},{"key":"34_CR5","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., et al.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"34_CR6","doi-asserted-by":"crossref","unstructured":"Ma, R., Peng, M., Zhang, Q., et al.: Simplify the usage of lexicon in Chinese NER. arXiv preprint arXiv:1908.05969 (2019)","DOI":"10.18653\/v1\/2020.acl-main.528"},{"key":"34_CR7","doi-asserted-by":"crossref","unstructured":"Jia, M., Shen, L., Shen, X., et al.: MNER-QG: an end-to-end MRC framework for multimodal named entity recognition with query grounding. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 37, no. 7, pp. 8032\u20138040 (2023)","DOI":"10.1609\/aaai.v37i7.25971"},{"key":"34_CR8","unstructured":"Yang, J., Liang, S., Zhang, Y.: Design challenges and misconceptions in neural sequence labeling. arXiv preprint arXiv:1806.04470 (2018)"},{"issue":"2","key":"34_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3604931","volume":"56","author":"M Ehrmann","year":"2023","unstructured":"Ehrmann, M., Hamdi, A., Pontes, E.L., et al.: Named entity recognition and classification in historical documents: a survey. ACM Comput. Surv. 56(2), 1\u201347 (2023)","journal-title":"ACM Comput. Surv."},{"key":"34_CR10","doi-asserted-by":"crossref","unstructured":"Lu, D., Neves, L., Carvalho, V., et al.: Visual attention model for name tagging in multimodal social media. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 1990\u20131999 (2018)","DOI":"10.18653\/v1\/P18-1185"},{"key":"34_CR11","doi-asserted-by":"crossref","unstructured":"Moon, S., Neves, L., Carvalho, V.: Multimodal named entity recognition for short social media posts. arXiv preprint arXiv:1802.07862 (2018)","DOI":"10.18653\/v1\/N18-1078"},{"issue":"1","key":"34_CR12","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1109\/TKDE.2018.2879819","volume":"32","author":"B Zheng","year":"2018","unstructured":"Zheng, B., Zheng, K., Jensen, C.S., et al.: Answering why-not group spatial keyword queries. IEEE Trans. Knowl. Data Eng. 32(1), 26\u201339 (2018)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"34_CR13","doi-asserted-by":"crossref","unstructured":"Li, W., Gao, C., Niu, G., et al.: Unimo-2: end-to-end unified vision-language grounded learning. arXiv preprint arXiv:2203.09067 (2022)","DOI":"10.18653\/v1\/2022.findings-acl.251"},{"key":"34_CR14","doi-asserted-by":"crossref","unstructured":"Sun, L., et al.: RpBERT: a text-image relation propagation-based BERT model for multimodal NER. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, no. 15, pp. 13860\u201313868 (2021)","DOI":"10.1609\/aaai.v35i15.17633"},{"issue":"4","key":"34_CR15","doi-asserted-by":"publisher","first-page":"927","DOI":"10.1109\/TMM.2017.2760101","volume":"20","author":"Y Hu","year":"2017","unstructured":"Hu, Y., et al.: Twitter100k: a real-world dataset for weakly supervised cross-media retrieval. IEEE Trans. Multimedia 20(4), 927\u2013938 (2017)","journal-title":"IEEE Trans. Multimedia"},{"key":"34_CR16","doi-asserted-by":"crossref","unstructured":"Guo, A., et al.: MGICL: multi-grained interaction contrastive learning for multimodal named entity recognition. In: Proceedings of the 32nd ACM International Conference on Information and Knowledge Management, pp. 639\u2013648 (2023)","DOI":"10.1145\/3583780.3614967"},{"key":"34_CR17","doi-asserted-by":"crossref","unstructured":"Yu, J., et al.: Grounded multimodal named entity recognition on social media. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 9141\u20139154 (2023)","DOI":"10.18653\/v1\/2023.acl-long.508"},{"key":"34_CR18","doi-asserted-by":"crossref","unstructured":"Nam, H., et al.: Dual attention networks for multimodal reasoning and matching. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 299\u2013307 (2017)","DOI":"10.1109\/CVPR.2017.232"},{"key":"34_CR19","unstructured":"Zong, C., et al.: Proceedings of the 59th annual meeting of the association for computational linguistics and the 11th international joint conference on natural language processing. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) (2021)"},{"issue":"5","key":"34_CR20","doi-asserted-by":"publisher","first-page":"643","DOI":"10.14778\/3377369.3377374","volume":"13","author":"B Zheng","year":"2020","unstructured":"Zheng, B., et al.: PM-LSH: a fast and accurate LSH framework for high-dimensional approximate NN search. Proc. VLDB Endow. 13(5), 643\u2013655 (2020)","journal-title":"Proc. VLDB Endow."},{"key":"34_CR21","unstructured":"Limsopatham, N., Collier, N.: Bidirectional LSTM for named entity recognition in Twitter messages. In: Proceedings of the 2nd Workshop on Noisy User-generated Text (WNUT), pp. 145\u2013152 (2016)"},{"key":"34_CR22","doi-asserted-by":"crossref","unstructured":"Yu, J., et al.: Improving multimodal named entity recognition via entity span detection with unified multimodal transformer. In: Association for Computational Linguistics (2020)","DOI":"10.18653\/v1\/2020.acl-main.306"},{"key":"34_CR23","doi-asserted-by":"crossref","unstructured":"Zhang, D., et al.: Multi-modal graph fusion for named entity recognition with targeted visual guidance. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, no. 16, pp. 14347\u201314355 (2021)","DOI":"10.1609\/aaai.v35i16.17687"},{"key":"34_CR24","doi-asserted-by":"crossref","unstructured":"Baltru\u0161aitis, T., Ahuja, C., Morency, L.P.: Multimodal machine learning: a survey and taxonomy. IEEE Trans. Pattern Anal. Mach. Intell. 41(2), 423\u2013443 (2018)","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"34_CR25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1613\/jair.4135","volume":"49","author":"E Bruni","year":"2014","unstructured":"Bruni, E., Tran, N.K., Baroni, M.: Multimodal distributional semantics. J. Artif. Intell. Res. 49, 1\u201347 (2014)","journal-title":"J. Artif. Intell. Res."},{"key":"34_CR26","doi-asserted-by":"crossref","unstructured":"Kiela, D., Bottou, L.: Learning image embeddings using convolutional neural networks for improved multi-modal semantics. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 36\u201345 (2014)","DOI":"10.3115\/v1\/D14-1005"},{"key":"34_CR27","doi-asserted-by":"crossref","unstructured":"Collell, G., Zhang, T., Moens, M.F.: Imagined visual representations as multimodal embeddings. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 31, no. 1 (2017)","DOI":"10.1609\/aaai.v31i1.11155"},{"key":"34_CR28","doi-asserted-by":"crossref","unstructured":"Peng, D., et al:. SAM-GAN: self-attention supporting multi-stage generative adversarial networks for text-to-image synthesis. Neural Netw. 138, 57\u201367 (2021)","DOI":"10.1016\/j.neunet.2021.01.023"},{"key":"34_CR29","doi-asserted-by":"crossref","unstructured":"Sang, E.F., Veenstra, J.: Representing text chunks. arXiv preprint cs\/9907006 (1999)","DOI":"10.3115\/977035.977059"},{"key":"34_CR30","doi-asserted-by":"crossref","unstructured":"Ju, X., et al:. Joint multi-modal aspect-sentiment analysis with auxiliary cross-modal relation detection. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 4395\u20134405 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.360"},{"key":"34_CR31","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"34_CR32","doi-asserted-by":"crossref","unstructured":"Zhang, Q., et al.: 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":"34_CR33","unstructured":"Huang, Z., Xu, W., Yu, K.: Bidirectional LSTM-CRF models for sequence tagging. arXiv preprint arXiv:1508.01991 (2015)"},{"key":"34_CR34","doi-asserted-by":"crossref","unstructured":"Ma, X., Hovy, E.: End-to-end sequence labeling via bi-directional LSTM-CNNS-CRF. arXiv preprint arXiv:1603.01354 (2016)","DOI":"10.18653\/v1\/P16-1101"},{"key":"34_CR35","doi-asserted-by":"crossref","unstructured":"Wu, Z., et al.: Multimodal representation with embedded visual guiding objects for named entity recognition in social media posts. In: MM \u201820: The 28th ACM International Conference on Multimedia, Virtual Event \/ Seattle, WA, USA, 12\u201316 October 2020, pp. 1038\u20131046 (2020)","DOI":"10.1145\/3394171.3413650"},{"key":"34_CR36","doi-asserted-by":"crossref","unstructured":"Wang, X., et al.: ITA: image-text alignments for multi-modal named entity recognition. arXiv preprint arXiv:2112.06482 (2021)","DOI":"10.18653\/v1\/2022.naacl-main.232"},{"key":"34_CR37","doi-asserted-by":"crossref","unstructured":"Xu, X., et al.: Bridgetower: building bridges between encoders in vision-language representation learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 37, no. 9, pp. 10637\u201310647 (2023)","DOI":"10.1609\/aaai.v37i9.26263"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-5669-8_34","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T17:14:34Z","timestamp":1722618874000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-5669-8_34"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819756681","9789819756698"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-5669-8_34","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"3 August 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tianjin","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 August 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 August 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":"icic2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2024\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}