{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,26]],"date-time":"2025-07-26T09:07:56Z","timestamp":1753520876346,"version":"3.40.3"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031306747"},{"type":"electronic","value":"9783031306754"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-30675-4_51","type":"book-chapter","created":{"date-parts":[[2023,4,14]],"date-time":"2023-04-14T10:02:24Z","timestamp":1681466544000},"page":"699-715","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Cross-Modal Contrastive Learning for\u00a0Event Extraction"],"prefix":"10.1007","author":[{"given":"Shuo","family":"Wang","sequence":"first","affiliation":[]},{"given":"Meizhi","family":"Ju","sequence":"additional","affiliation":[]},{"given":"Yunyan","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Yefeng","family":"Zheng","sequence":"additional","affiliation":[]},{"given":"Meng","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Guilin","family":"Qi","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,4,15]]},"reference":[{"key":"51_CR1","doi-asserted-by":"crossref","unstructured":"Chen, B., et al.: Joint multimedia event extraction from video and article. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing, pp. 74\u201388 (2021)","DOI":"10.18653\/v1\/2021.findings-emnlp.8"},{"key":"51_CR2","doi-asserted-by":"crossref","unstructured":"Chen, H., Shu, R., Takamura, H., Nakayama, H.: GraphPlan: story generation by planning with event graph. In: Proceedings of the 14th International Conference on Natural Language Generation, pp. 377\u2013386 (2021)","DOI":"10.18653\/v1\/2021.inlg-1.42"},{"key":"51_CR3","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine learning, pp. 1597\u20131607 (2020)"},{"key":"51_CR4","doi-asserted-by":"crossref","unstructured":"Daiya, D.: Combining temporal event relations and pre-trained language models for text summarization. In: IEEE International Conference on Machine Learning and Applications, pp. 641\u2013646 (2020)","DOI":"10.1109\/ICMLA51294.2020.00106"},{"key":"51_CR5","doi-asserted-by":"crossref","unstructured":"Du, X., Cardie, C.: Event extraction by answering (almost) natural questions. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing, pp. 671\u2013683 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.49"},{"key":"51_CR6","doi-asserted-by":"crossref","unstructured":"Du, X., Rush, A.M., Cardie, C.: GRiT: generative role-filler transformers for document-level event entity extraction. In: Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pp. 634\u2013644 (2021)","DOI":"10.18653\/v1\/2021.eacl-main.52"},{"key":"51_CR7","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9729\u20139738 (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"51_CR8","doi-asserted-by":"crossref","unstructured":"Huang, P.Y., Patrick, M., Hu, J., Neubig, G., Metze, F., Hauptmann, A.: Multilingual multimodal pre-training for zero-shot cross-lingual transfer of vision-language models. arXiv preprint arXiv:2103.08849 (2021)","DOI":"10.18653\/v1\/2021.naacl-main.195"},{"key":"51_CR9","unstructured":"Kenton, J.D.M.W.C., Toutanova, L.K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics, pp. 4171\u20134186 (2019)"},{"key":"51_CR10","doi-asserted-by":"crossref","unstructured":"Li, M., et al.: Timeline summarization based on event graph compression via time-aware optimal transport. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing, pp. 6443\u20136456 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.519"},{"key":"51_CR11","doi-asserted-by":"crossref","unstructured":"Li, M., et al.: Cross-media structured common space for multimedia event extraction. In: Proceedings of Annual Meeting of the Association for Computational Linguistics, pp. 2557\u20132568 (2020)","DOI":"10.18653\/v1\/2020.acl-main.230"},{"key":"51_CR12","unstructured":"Li, Q., Ji, H., Huang, L.: Joint event extraction via structured prediction with global features. In: Proceedings of Annual Meeting of the Association for Computational Linguistics, vol. 1, pp. 73\u201382 (2013)"},{"key":"51_CR13","doi-asserted-by":"crossref","unstructured":"Lin, Y., Ji, H., Huang, F., Wu, L.: A joint neural model for information extraction with global features. In: Proceedings of Annual Meeting of the Association for Computational Linguistics, pp. 7999\u20138009. Association for Computational Linguistics, (2020)","DOI":"10.18653\/v1\/2020.acl-main.713"},{"key":"51_CR14","unstructured":"Lu, J., Batra, D., Parikh, D., Lee, S.: ViLBERT: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. In: Advances in Neural Information Processing Systems, pp. 13\u201323 (2019)"},{"key":"51_CR15","doi-asserted-by":"crossref","unstructured":"Martschat, S., Markert, K.: A temporally sensitive submodularity framework for timeline summarization. In: Proceedings of the Conference on Computational Natural Language Learning, pp. 230\u2013240 (2018)","DOI":"10.18653\/v1\/K18-1023"},{"key":"51_CR16","doi-asserted-by":"crossref","unstructured":"Nguyen, T.H., Cho, K., Grishman, R.: Joint event extraction via recurrent neural networks. In: Proceedings of Annual Meeting of the Association for Computational Linguistics, pp. 300\u2013309 (2016)","DOI":"10.18653\/v1\/N16-1034"},{"key":"51_CR17","doi-asserted-by":"crossref","unstructured":"Nguyen, T.H., Grishman, R.: Event detection and domain adaptation with convolutional neural networks. In: Proceedings of the Annual Meeting of the Association for Computational Linguistics and the International Joint Conference on Natural Language Processing, pp. 365\u2013371 (2015)","DOI":"10.3115\/v1\/P15-2060"},{"key":"51_CR18","doi-asserted-by":"crossref","unstructured":"Pratt, S., Yatskar, M., Weihs, L., Farhadi, A., Kembhavi, A.: Grounded situation recognition. In: European Conference on Computer Vision, pp. 314\u2013332 (2020)","DOI":"10.1007\/978-3-030-58548-8_19"},{"issue":"140","key":"51_CR19","first-page":"1","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21(140), 1\u201367 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"51_CR20","doi-asserted-by":"crossref","unstructured":"Sadhu, A., Gupta, T., Yatskar, M., Nevatia, R., Kembhavi, A.: Visual semantic role labeling for video understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5589\u20135600 (2021)","DOI":"10.1109\/CVPR46437.2021.00554"},{"issue":"5","key":"51_CR21","first-page":"9040","volume":"34","author":"M Tong","year":"2020","unstructured":"Tong, M., et al.: Image enhanced event detection in news articles. Proceed. AAAI Conf. Artif. Intell. 34(5), 9040\u20139047 (2020)","journal-title":"Proceed. AAAI Conf. Artif. Intell."},{"key":"51_CR22","doi-asserted-by":"crossref","unstructured":"Wadden, D., Wennberg, U., Luan, Y., Hajishirzi, H.: Entity, relation, and event extraction with contextualized span representations. arXiv preprint arXiv:1909.03546 (2019)","DOI":"10.18653\/v1\/D19-1585"},{"key":"51_CR23","first-page":"45","volume":"57","author":"C Walker","year":"2006","unstructured":"Walker, C., Strassel, S., Medero, J., Maeda, K.: ACE 2005 multilingual training corpus. Linguist. Data Consort. Philadelp. 57, 45 (2006)","journal-title":"Linguist. Data Consort. Philadelp."},{"key":"51_CR24","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: CLEVE: contrastive pre-training for event extraction. In: Proceedings of Conference on Empirical Methods in Natural Language Processing and International Joint Conference on Natural Language Processing. vol. 1, pp. 6283\u20136297 (2021)","DOI":"10.18653\/v1\/2021.acl-long.491"},{"key":"51_CR25","doi-asserted-by":"crossref","unstructured":"Yao, S., Yang, J., Lu, X., Shuang, K.: Contrastive learning for event extraction. In: International Conference on Machine Learning and Soft Computing, pp. 167\u2013172 (2022)","DOI":"10.1145\/3523150.3523176"},{"key":"51_CR26","doi-asserted-by":"crossref","unstructured":"Yeh, Y.T., Chen, Y.N.: QAInfomax: learning robust question answering system by mutual information maximization. In: Proceedings of Conference on Empirical Methods in Natural Language Processing and International Joint Conference on Natural Language Processing, pp. 3370\u20133375 (2019)","DOI":"10.18653\/v1\/D19-1333"},{"key":"51_CR27","doi-asserted-by":"crossref","unstructured":"Zhang, H., Koh, J.Y., Baldridge, J., Lee, H., Yang, Y.: Cross-modal contrastive learning for text-to-image generation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 833\u2013842 (2021)","DOI":"10.1109\/CVPR46437.2021.00089"},{"key":"51_CR28","doi-asserted-by":"crossref","unstructured":"Zhang, S., Song, L., Jin, L., Xu, K., Yu, D., Luo, J.: Video-aided unsupervised grammar induction. In: Proceedings of Annual Meeting of the Association for Computational Linguistics, pp. 1513\u20131524 (2021)","DOI":"10.18653\/v1\/2021.naacl-main.119"},{"key":"51_CR29","doi-asserted-by":"crossref","unstructured":"Zhang, T., et al.: Improving event extraction via multimodal integration. In: Proceedings of ACM International Conference on Multimedia, pp. 270\u2013278 (2017)","DOI":"10.1145\/3123266.3123294"},{"key":"51_CR30","doi-asserted-by":"crossref","unstructured":"Zolfaghari, M., Zhu, Y., Gehler, P., Brox, T.: CrossCLR: cross-modal contrastive learning for multi-modal video representations. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1450\u20131459 (2021)","DOI":"10.1109\/ICCV48922.2021.00148"}],"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\/978-3-031-30675-4_51","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,18]],"date-time":"2024-10-18T08:47:29Z","timestamp":1729241249000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-30675-4_51"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031306747","9783031306754"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-30675-4_51","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"15 April 2023","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":"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":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 April 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 April 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"dasfaa2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.tjudb.cn\/dasfaa2023\/","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":"652","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":"125","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":"66","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":"19% - 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","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":"7.3","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)"}}]}}