Abstract
Event extraction aims to extract information of triggers and arguments from texts. Recent advanced methods leverage information from other modalities (e.g., images and videos) besides the texts to enhance event extraction. However, the different modalities are often misaligned at the event level, negatively impacting model performance. To address this issue, we firstly constructed a new multi-modal event extraction benchmark Text Video Event Extraction (TVEE) dataset, containing 7,598 text-video pairs. The texts are automatically extracted from video captions, which are perfectly aligned to the video content in most cases. Secondly, we present a Cross-modal Contrastive Learning for Event Extraction (CoCoEE) model to extract events from multi-modal data by contrasting text-video and event-video representations. We conduct extensive experiments on our TVEE dataset and the current benchmark VM2E2 dataset. The results show that our proposed model outperforms baseline methods in terms of F-score. Furthermore, the proposed cross-modal contrastive learning method improves event extraction in each single modality. The dataset and code will be released once upon acceptance.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
- 2.
- 3.
- 4.
- 5.
Because the multi-modal evaluation only focuses on event type extraction, it can’t show the performance of every module, we perform ablation study on text evaluation and video evaluation.
References
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. 74–88 (2021)
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. 377–386 (2021)
Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine learning, pp. 1597–1607 (2020)
Daiya, D.: Combining temporal event relations and pre-trained language models for text summarization. In: IEEE International Conference on Machine Learning and Applications, pp. 641–646 (2020)
Du, X., Cardie, C.: Event extraction by answering (almost) natural questions. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing, pp. 671–683 (2020)
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. 634–644 (2021)
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. 9729–9738 (2020)
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)
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. 4171–4186 (2019)
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. 6443–6456 (2021)
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. 2557–2568 (2020)
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. 73–82 (2013)
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. 7999–8009. Association for Computational Linguistics, (2020)
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. 13–23 (2019)
Martschat, S., Markert, K.: A temporally sensitive submodularity framework for timeline summarization. In: Proceedings of the Conference on Computational Natural Language Learning, pp. 230–240 (2018)
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. 300–309 (2016)
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. 365–371 (2015)
Pratt, S., Yatskar, M., Weihs, L., Farhadi, A., Kembhavi, A.: Grounded situation recognition. In: European Conference on Computer Vision, pp. 314–332 (2020)
Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21(140), 1–67 (2020)
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. 5589–5600 (2021)
Tong, M., et al.: Image enhanced event detection in news articles. Proceed. AAAI Conf. Artif. Intell. 34(5), 9040–9047 (2020)
Wadden, D., Wennberg, U., Luan, Y., Hajishirzi, H.: Entity, relation, and event extraction with contextualized span representations. arXiv preprint arXiv:1909.03546 (2019)
Walker, C., Strassel, S., Medero, J., Maeda, K.: ACE 2005 multilingual training corpus. Linguist. Data Consort. Philadelp. 57, 45 (2006)
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. 6283–6297 (2021)
Yao, S., Yang, J., Lu, X., Shuang, K.: Contrastive learning for event extraction. In: International Conference on Machine Learning and Soft Computing, pp. 167–172 (2022)
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. 3370–3375 (2019)
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. 833–842 (2021)
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. 1513–1524 (2021)
Zhang, T., et al.: Improving event extraction via multimodal integration. In: Proceedings of ACM International Conference on Multimedia, pp. 270–278 (2017)
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. 1450–1459 (2021)
Acknowledgments
Supported by the National Key Research and Development Program of China (No. 2022YFF0712400), the National Natural Science Foundation of China (No. 62276063), and the Natural Science Foundation of Jiangsu Province under Grants No. BK20221457.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Wang, S., Ju, M., Zhang, Y., Zheng, Y., Wang, M., Qi, G. (2023). Cross-Modal Contrastive Learning for Event Extraction. In: Wang, X., et al. Database Systems for Advanced Applications. DASFAA 2023. Lecture Notes in Computer Science, vol 13945. Springer, Cham. https://doi.org/10.1007/978-3-031-30675-4_51
Download citation
DOI: https://doi.org/10.1007/978-3-031-30675-4_51
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-30674-7
Online ISBN: 978-3-031-30675-4
eBook Packages: Computer ScienceComputer Science (R0)