{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,14]],"date-time":"2026-06-14T22:53:56Z","timestamp":1781477636952,"version":"3.54.1"},"publisher-location":"Singapore","reference-count":36,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819541485","type":"print"},{"value":"9789819541492","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-981-95-4149-2_25","type":"book-chapter","created":{"date-parts":[[2026,6,14]],"date-time":"2026-06-14T22:48:17Z","timestamp":1781477297000},"page":"376-391","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Retrieval-Based Multimodal Data Augmentation for\u00a0Multimodal Information Extraction in\u00a0Social Media"],"prefix":"10.1007","author":[{"given":"Shizhou","family":"Huang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Changqun","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,2]]},"reference":[{"key":"25_CR1","unstructured":"Chen, F., Feng, Y.: Chain-of-thought prompt distillation for multimodal named entity and multimodal relation extraction. arXiv preprint arXiv:2306.14122 (2023)"},{"key":"25_CR2","doi-asserted-by":"publisher","unstructured":"Chen, S., Aguilar, G., Neves, L., Solorio, T.: Data augmentation for cross-domain named entity recognition. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 5346\u20135356. Association for Computational Linguistics (2021). https:\/\/doi.org\/10.18653\/v1\/2021.emnlp-main.434","DOI":"10.18653\/v1\/2021.emnlp-main.434"},{"key":"25_CR3","doi-asserted-by":"publisher","unstructured":"Chen, X., et al.: Good visual guidance make a better extractor: hierarchical visual prefix for multimodal entity and relation extraction. In: Findings of the Association for Computational Linguistics: NAACL 2022, pp. 1607\u20131618. Association for Computational Linguistics (2022). https:\/\/doi.org\/10.18653\/v1\/2022.findings-naacl.121","DOI":"10.18653\/v1\/2022.findings-naacl.121"},{"key":"25_CR4","doi-asserted-by":"publisher","unstructured":"Dai, X., Adel, H.: An analysis of simple data augmentation for named entity recognition. In: Proceedings of the 28th International Conference on Computational Linguistics, pp. 3861\u20133867. International Committee on Computational Linguistics (2020). https:\/\/doi.org\/10.18653\/v1\/2020.coling-main.343","DOI":"10.18653\/v1\/2020.coling-main.343"},{"key":"25_CR5","doi-asserted-by":"crossref","unstructured":"Ding, B., et al.: DAGA: data augmentation with a generation approach for low-resource tagging tasks. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 6045\u20136057 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.488"},{"key":"25_CR6","doi-asserted-by":"crossref","unstructured":"Ding, G., Jiang, T., Zhou, R., Gao, Q.: ALDF: an adaptive logical decision framework for multimodal named entity recognition. In: Proceedings of the 33rd ACM International Conference on Information and Knowledge Management, pp. 436\u2013445 (2024)","DOI":"10.1145\/3627673.3679706"},{"key":"25_CR7","doi-asserted-by":"publisher","unstructured":"Gao, T., Yao, X., Chen, D.: SimCSE: simple contrastive learning of sentence embeddings. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 6894\u20136910. Association for Computational Linguistics (2021). https:\/\/doi.org\/10.18653\/v1\/2021.emnlp-main.552","DOI":"10.18653\/v1\/2021.emnlp-main.552"},{"key":"25_CR8","doi-asserted-by":"publisher","unstructured":"Hu, X., Chen, J., Liu, A., Meng, S., Wen, L., Yu, P.S.: Prompt me up: unleashing the power of alignments for multimodal entity and relation extraction. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 5185\u20135194. ACM (2023). https:\/\/doi.org\/10.1145\/3581783.3611899","DOI":"10.1145\/3581783.3611899"},{"key":"25_CR9","doi-asserted-by":"crossref","unstructured":"Huang, S., Xu, B., Li, C., Ye, J., Lin, X.: MNER-MI: a multi-image dataset for multimodal named entity recognition in social media. In: Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pp. 11452\u201311462 (2024)","DOI":"10.63317\/26e4yx7gpgmd"},{"key":"25_CR10","doi-asserted-by":"crossref","unstructured":"Jia, M., 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.\u00a037, pp. 8032\u20138040 (2023)","DOI":"10.1609\/aaai.v37i7.25971"},{"key":"25_CR11","doi-asserted-by":"crossref","unstructured":"Jia, M., et al.: Query prior matters: a MRC framework for multimodal named entity recognition. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 3549\u20133558 (2022)","DOI":"10.1145\/3503161.3548427"},{"key":"25_CR12","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":"25_CR13","doi-asserted-by":"crossref","unstructured":"Liu, X., Hu, C., Zhang, R., Sun, K., Mensah, S., Mao, Y.: Multimodal relation extraction via a mixture of hierarchical visual context learners. In: Proceedings of the ACM on Web Conference 2024, pp. 4283\u20134294 (2024)","DOI":"10.1145\/3589334.3645603"},{"key":"25_CR14","unstructured":"Liu, Y., et al.: RoBERTa: a robustly optimized BERT pretraining approach. arXiv preprint arXiv:1907.11692 (2019)"},{"key":"25_CR15","doi-asserted-by":"publisher","unstructured":"Lu, D., Neves, L., Carvalho, V., Zhang, N., Ji, H.: 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. Association for Computational Linguistics (2018). https:\/\/doi.org\/10.18653\/v1\/p18-1185","DOI":"10.18653\/v1\/p18-1185"},{"key":"25_CR16","doi-asserted-by":"publisher","unstructured":"Moon, S., Neves, L., Carvalho, V.: Multimodal named entity recognition for short social media posts. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pp. 852\u2013860. Association for Computational Linguistics (2018). https:\/\/doi.org\/10.18653\/v1\/n18-1078","DOI":"10.18653\/v1\/n18-1078"},{"issue":"1","key":"25_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3445965","volume":"54","author":"Z Nasar","year":"2021","unstructured":"Nasar, Z., Jaffry, S.W., Malik, M.K.: Named entity recognition and relation extraction: state-of-the-art. ACM Comput. Surv. (CSUR) 54(1), 1\u201339 (2021). https:\/\/doi.org\/10.1145\/3445965","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"25_CR18","doi-asserted-by":"publisher","unstructured":"Nguyen, D.Q., Vu, T., Nguyen, A.T.: BERTweet: a pre-trained language model for english tweets. EMNLP 2020, 9 (2020). https:\/\/doi.org\/10.18653\/v1\/2020.emnlp-demos.2","DOI":"10.18653\/v1\/2020.emnlp-demos.2"},{"key":"25_CR19","doi-asserted-by":"publisher","unstructured":"Nie, Y., Tian, Y., Wan, X., Song, Y., Dai, B.: Named entity recognition for social media texts with semantic augmentation. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1383\u20131391. Association for Computational Linguistics (2020). https:\/\/doi.org\/10.18653\/v1\/2020.emnlp-main.107","DOI":"10.18653\/v1\/2020.emnlp-main.107"},{"key":"25_CR20","doi-asserted-by":"publisher","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, vol.\u00a035, pp. 13860\u201313868. Association for the Advancement of Artificial Intelligence (AAAI) (2021). https:\/\/doi.org\/10.1609\/aaai.v35i15.17633","DOI":"10.1609\/aaai.v35i15.17633"},{"key":"25_CR21","doi-asserted-by":"crossref","unstructured":"Sun, L., Zhang, K., Li, Q., Lou, R.: UMIE: unified multimodal information extraction with instruction tuning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 19062\u201319070 (2024)","DOI":"10.1609\/aaai.v38i17.29873"},{"key":"25_CR22","doi-asserted-by":"publisher","unstructured":"Tang, K., Niu, Y., Huang, J., Shi, J., Zhang, H.: Unbiased scene graph generation from biased training. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3716\u20133725 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00377","DOI":"10.1109\/CVPR42600.2020.00377"},{"key":"25_CR23","doi-asserted-by":"publisher","unstructured":"Wang, X., Cai, J., Jiang, Y., Xie, P., Tu, K., Lu, W.: Named entity and relation extraction with multi-modal retrieval. In: Findings of the Association for Computational Linguistics: EMNLP 2022, pp. 5925\u20135936 (2022). https:\/\/doi.org\/10.18653\/v1\/2022.findings-emnlp.437","DOI":"10.18653\/v1\/2022.findings-emnlp.437"},{"key":"25_CR24","doi-asserted-by":"publisher","unstructured":"Wang, X., et al.: ITA: image-text alignments for multi-modal named entity recognition. In: Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 3176\u20133189. Association for Computational Linguistics (2022). https:\/\/doi.org\/10.18653\/v1\/2022.naacl-main.232","DOI":"10.18653\/v1\/2022.naacl-main.232"},{"key":"25_CR25","doi-asserted-by":"crossref","unstructured":"Wei, P., Huang, Z., Ouyang, H., Hu, Q., Zeng, B., Feng, G.: CGI-MRE: a comprehensive genetic-inspired model for multimodal relation extraction. In: Proceedings of the 2024 International Conference on Multimedia Retrieval, pp. 524\u2013532 (2024)","DOI":"10.1145\/3652583.3658103"},{"key":"25_CR26","doi-asserted-by":"publisher","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: Proceedings of the 28th ACM International Conference on Multimedia, pp. 1038\u20131046. ACM (2020). https:\/\/doi.org\/10.1145\/3394171.3413650","DOI":"10.1145\/3394171.3413650"},{"key":"25_CR27","unstructured":"Xu, B., Huang, S., Du, M., Wang, H., Song, H., Sha, C., Xiao, Y.: Different data, different modalities! reinforced data splitting for effective multimodal information extraction from social media posts. In: Proceedings of the 29th International Conference on Computational Linguistics, pp. 1855\u20131864. International Committee on Computational Linguistics (2022). https:\/\/aclanthology.org\/2022.coling-1.160"},{"key":"25_CR28","doi-asserted-by":"publisher","unstructured":"Xu, B., Huang, S., Du, M., Wang, H., Song, H., Xiao, Y., Lin, X.: A unified visual prompt tuning framework with mixture-of-experts for multimodal information extraction. In: International Conference on Database Systems for Advanced Applications, pp. 544\u2013554. Springer, Springer Nature Switzerland (2023). https:\/\/doi.org\/10.1007\/978-3-031-30675-4_40","DOI":"10.1007\/978-3-031-30675-4_40"},{"key":"25_CR29","doi-asserted-by":"publisher","unstructured":"Xu, B., Huang, S., Sha, C., Wang, H.: MAF: a general matching and alignment framework for multimodal named entity recognition. In: Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining, pp. 1215\u20131223. ACM (2022). https:\/\/doi.org\/10.1145\/3488560.3498475","DOI":"10.1145\/3488560.3498475"},{"key":"25_CR30","unstructured":"Ye, J., et al.: LLM-DA: data augmentation via large language models for few-shot named entity recognition. arXiv preprint arXiv:2402.14568 (2024)"},{"key":"25_CR31","doi-asserted-by":"publisher","unstructured":"Yu, J., Jiang, J., Yang, L., Xia, R.: Improving multimodal named entity recognition via entity span detection with unified multimodal transformer. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 3342\u20133352. Association for Computational Linguistics (2020). https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.306","DOI":"10.18653\/v1\/2020.acl-main.306"},{"key":"25_CR32","doi-asserted-by":"publisher","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, vol.\u00a035, pp. 14347\u201314355. Association for the Advancement of Artificial Intelligence (AAAI) (2021).https:\/\/doi.org\/10.1609\/aaai.v35i16.17687","DOI":"10.1609\/aaai.v35i16.17687"},{"key":"25_CR33","doi-asserted-by":"publisher","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.\u00a032 (2018). https:\/\/doi.org\/10.1609\/aaai.v32i1.11962","DOI":"10.1609\/aaai.v32i1.11962"},{"key":"25_CR34","doi-asserted-by":"publisher","unstructured":"Zheng, C., Feng, J., Cai, Y., Wei, X., Li, Q.: Rethinking multimodal entity and relation extraction from a translation point of view. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 6810\u20136824. Association for Computational Linguistics (2023). https:\/\/doi.org\/10.18653\/v1\/2023.acl-long.376","DOI":"10.18653\/v1\/2023.acl-long.376"},{"key":"25_CR35","doi-asserted-by":"publisher","unstructured":"Zheng, C., Feng, J., Fu, Z., Cai, Y., Li, Q., Wang, T.: Multimodal relation extraction with efficient graph alignment. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 5298\u20135306. ACM (2021). https:\/\/doi.org\/10.1145\/3474085.3476968","DOI":"10.1145\/3474085.3476968"},{"key":"25_CR36","doi-asserted-by":"crossref","unstructured":"Zhou, R., Li, X., He, R., Bing, L., Cambria, E., Si, L., Miao, C.: MELM: data augmentation with masked entity language modeling for low-resource NER. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 2251\u20132262 (2022)","DOI":"10.18653\/v1\/2022.acl-long.160"}],"container-title":["Lecture Notes in Computer Science","Database Systems for Advanced Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-4149-2_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,14]],"date-time":"2026-06-14T22:48:20Z","timestamp":1781477300000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-4149-2_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819541485","9789819541492"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-4149-2_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"2 July 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DASFAA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Database Systems for Advanced Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Singapore","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Singapore","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 May 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 May 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"dasfaa2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/dasfaa2025.github.io","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}