{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T08:24:45Z","timestamp":1742977485293,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":28,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819794362"},{"type":"electronic","value":"9789819794379"}],"license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"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\/978-981-97-9437-9_27","type":"book-chapter","created":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T16:31:35Z","timestamp":1730392295000},"page":"343-355","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Multilevel Interaction Network Framework for\u00a0Multimodal Entity Linking"],"prefix":"10.1007","author":[{"given":"Xiaoyu","family":"Jia","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minghua","family":"Nuo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,1]]},"reference":[{"key":"27_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"463","DOI":"10.1007\/978-3-030-45439-5_31","volume-title":"Advances in Information Retrieval","author":"O Adjali","year":"2020","unstructured":"Adjali, O., Besan\u00e7on, R., Ferret, O., Le Borgne, H., Grau, B.: Multimodal entity linking for tweets. In: Jose, J.M., et al. (eds.) ECIR 2020. LNCS, vol. 12035, pp. 463\u2013478. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-45439-5_31"},{"key":"27_CR2","doi-asserted-by":"crossref","unstructured":"Blanco, R., Ottaviano, G., Meij, E.: Fast and space-efficient entity linking for queries. In: Proceedings of the Eighth ACM International Conference on Web Search and Data Mining, pp. 179\u2013188 (2015)","DOI":"10.1145\/2684822.2685317"},{"key":"27_CR3","doi-asserted-by":"crossref","unstructured":"Dill, S., et\u00a0al.: Semtag and seeker: bootstrapping the semantic web via automated semantic annotation. In: Proceedings of the 12th International Conference on World Wide Web, pp. 178\u2013186 (2003)","DOI":"10.1145\/775152.775178"},{"key":"27_CR4","doi-asserted-by":"crossref","unstructured":"Dou, Z.Y., et\u00a0al.: An empirical study of training end-to-end vision-and-language transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18166\u201318176 (2022)","DOI":"10.1109\/CVPR52688.2022.01763"},{"key":"27_CR5","doi-asserted-by":"crossref","unstructured":"Eshel, Y., Cohen, N., Radinsky, K., Markovitch, S., Yamada, I., Levy, O.: Named entity disambiguation for noisy text. In: Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017), pp. 58\u201368 (2017)","DOI":"10.18653\/v1\/K17-1008"},{"key":"27_CR6","doi-asserted-by":"crossref","unstructured":"Francis-Landau, M., Durrett, G., Klein, D.: Capturing semantic similarity for entity linking with convolutional neural networks. In: Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 1256\u20131261 (2016)","DOI":"10.18653\/v1\/N16-1150"},{"key":"27_CR7","doi-asserted-by":"crossref","unstructured":"Ganea, O.E., Hofmann, T.: Deep joint entity disambiguation with local neural attention. In: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pp. 2619\u20132629 (2017)","DOI":"10.18653\/v1\/D17-1277"},{"key":"27_CR8","doi-asserted-by":"crossref","unstructured":"Hasibi, F., Balog, K., Bratsberg, S.E.: Exploiting entity linking in queries for entity retrieval. In: Proceedings of the 2016 ACM International Conference on the Theory of Information Retrieval, pp. 209\u2013218 (2016)","DOI":"10.1145\/2970398.2970406"},{"key":"27_CR9","unstructured":"Hoffart, J., et al.: Robust disambiguation of named entities in text. In: Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing, pp. 782\u2013792 (2011)"},{"key":"27_CR10","unstructured":"Kenton, J.D.M.W.C., Toutanova, L.K.: Bert: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of NAACL-HLT, pp. 4171\u20134186 (2019)"},{"key":"27_CR11","unstructured":"Kim, W., Son, B., Kim, I.: Vilt: vision-and-language transformer without convolution or region supervision. In: International Conference on Machine Learning, pp. 5583\u20135594. PMLR (2021)"},{"key":"27_CR12","doi-asserted-by":"crossref","unstructured":"Kolitsas, N., Ganea, O.E., Hofmann, T.: End-to-end neural entity linking. In: Proceedings of the 22nd Conference on Computational Natural Language Learning, pp. 519\u2013529 (2018)","DOI":"10.18653\/v1\/K18-1050"},{"key":"27_CR13","doi-asserted-by":"crossref","unstructured":"Le, P., Titov, I.: Improving entity linking by modeling latent relations between mentions. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, vol. 1: Long Papers, pp. 1595\u20131604 (2018)","DOI":"10.18653\/v1\/P18-1148"},{"key":"27_CR14","unstructured":"Liu, Y., et al.: Roberta: a robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)"},{"key":"27_CR15","unstructured":"Lu, J., Yang, J., Batra, D., Parikh, D.: Hierarchical question-image co-attention for visual question answering. Adv. Neural Inf. Process. Syst. 29 (2016)"},{"key":"27_CR16","doi-asserted-by":"crossref","unstructured":"Luo, P., Xu, T., Wu, S., Zhu, C., Xu, L., Chen, E.: Multi-grained multimodal interaction network for entity linking. In: Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pp. 1583\u20131594 (2023)","DOI":"10.1145\/3580305.3599439"},{"key":"27_CR17","doi-asserted-by":"crossref","unstructured":"Mihalcea, R., Csomai, A.: Wikify! linking documents to encyclopedic knowledge. In: Proceedings of the Sixteenth ACM Conference on Conference on Information and Knowledge Management, pp. 233\u2013242 (2007)","DOI":"10.1145\/1321440.1321475"},{"key":"27_CR18","doi-asserted-by":"crossref","unstructured":"Milne, D., Witten, I.H.: Learning to link with wikipedia. In: Proceedings of the 17th ACM Conference on Information and Knowledge Management, pp. 509\u2013518 (2008)","DOI":"10.1145\/1458082.1458150"},{"key":"27_CR19","doi-asserted-by":"crossref","unstructured":"Moon, S., Neves, L., Carvalho, V.: Multimodal named entity disambiguation for noisy social media posts. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, vol. 1: Long Papers, pp. 2000\u20132008 (2018)","DOI":"10.18653\/v1\/P18-1186"},{"key":"27_CR20","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"27_CR21","doi-asserted-by":"crossref","unstructured":"Ran, C., Shen, W., Wang, J.: An attention factor graph model for tweet entity linking. In: Proceedings of the 2018 World Wide Web Conference, pp. 1135\u20131144 (2018)","DOI":"10.1145\/3178876.3186012"},{"key":"27_CR22","doi-asserted-by":"crossref","unstructured":"Shah, S., Mishra, A., Yadati, N., Talukdar, P.P.: Kvqa: knowledge-aware visual question answering. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a033, pp. 8876\u20138884 (2019)","DOI":"10.1609\/aaai.v33i01.33018876"},{"key":"27_CR23","unstructured":"Sun, Y., Lin, L., Tang, D., Yang, N., Ji, Z., Wang, X.: Modeling mention, context and entity with neural networks for entity disambiguation. In: Proceedings of the 24th International Conference on Artificial Intelligence, pp. 1333\u20131339 (2015)"},{"key":"27_CR24","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818\u20132826 (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"27_CR25","doi-asserted-by":"crossref","unstructured":"Wang, P., Wu, J., Chen, X.: Multimodal entity linking with gated hierarchical fusion and contrastive training. In: Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 938\u2013948 (2022)","DOI":"10.1145\/3477495.3531867"},{"key":"27_CR26","doi-asserted-by":"crossref","unstructured":"Wang, X., et al.: Wikidiverse: a multimodal entity linking dataset with diversified contextual topics and entity types. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics, vol, 1: Long Papers, pp. 4785\u20134797 (2022)","DOI":"10.18653\/v1\/2022.acl-long.328"},{"key":"27_CR27","doi-asserted-by":"crossref","unstructured":"Wu, L., Petroni, F., Josifoski, M., Riedel, S., Zettlemoyer, L.: Scalable zero-shot entity linking with dense entity retrieval. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 6397\u20136407 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.519"},{"key":"27_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1007\/978-3-030-73197-7_35","volume-title":"Database Systems for Advanced Applications","author":"L Zhang","year":"2021","unstructured":"Zhang, L., Li, Z., Yang, Q.: Attention-based multimodal entity linking with high-quality images. In: Jensen, C.S., et al. (eds.) DASFAA 2021. LNCS, vol. 12682, pp. 533\u2013548. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-73197-7_35"}],"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\/978-981-97-9437-9_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T16:32:41Z","timestamp":1730392361000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-9437-9_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,1]]},"ISBN":["9789819794362","9789819794379"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-9437-9_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,1]]},"assertion":[{"value":"1 November 2024","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":"Hangzhou","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":"2 November 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 November 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"nlpcc2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/tcci.ccf.org.cn\/conference\/2024\/index.php","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}