Abstract
Script event prediction aims to predict the most likely following events, given the historical events in the script. This task requires the capability to learn more information between events. Most previous methods mainly focused on the current local information, while ignoring more inner semantic features of events. In this work, we propose a novel framework, called ECer, which can obtain more comprehensive event information by utilizing data augmentation and information integration. We first employ rectified linear attention to connect the initial event representation at the argument level. Then, to learn richer semantic information, data augmentation is further applied to expand data and introduce external knowledge. Furthermore, the initial representation and the features of augmented data were mixed by Mixup. Finally, an attention module is applied to the context event chain to integrate context events concerning the current candidate event dynamically. The experimental results on the widely-used New York Times corpus demonstrate the effectiveness and superiority of the proposed model.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Schank, R.C., Abelson, R.P.: Scripts, plans, and knowledge. IJCAI 75, 151–157. Morgan Kaufmann Publishers Inc, San Francisco (1975)
Mikolov, T., Sutskever, I., Chen, K., et al.: Distributed representations of words and phrases and their compositionality. Advances in neural information processing systems. Journal 26(2), 3111–3119 (2013)
Mikolov, T., Chen, K., Corrado, G., et al.: Efficient estimation of word representations in vector space. arXiv preprint arXiv (2013)
Weber, N., Balasubramanian, N., Chambers, N.: Event representations with tensor-based compositions. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 4946–4953. AAAI Press, Palo Alto (2018)
Socher, R., Huval, B., Manning, C.D., et al.: Semantic compositionality through recursive matrix-vector spaces. In: Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, pp. 1201–1211. ACL Press, Jeju Island (2012)
Ding, X., Liao, K., Liu, T., et al.: Event representation learning enhanced with external commonsense knowledge. arXiv preprint arXiv (2019)
Chambers, N., Jurafsky, D.: Unsupervised learning of narrative event chains. In: Proceedings of ACL-08, pp.789–797. ACL Press, Columbus (2008)
Pichotta, K., Mooney, R.: Statistical script learning with multi-argument events. In: Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics, pp. 220–229. ACL Press, Sweden (2014)
Luan, F., Paris, S., Shechtman, E., et al.: Deep photo style transfer. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4990–4998 (2017)
Mueller, J., Thyagarajan, A.: Siamese recurrent architectures for learning sentence similarity. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 30 (2016)
Xie, Q., Dai, Z., Hovy, E., et al.: Unsupervised data augmentation for consistency training. arXiv preprint arXiv (2019)
Coulombe, C.: Text data augmentation made simple by leveraging NLP cloud APIs. arXiv preprint arXiv (2018)
Yan, G., Li, Y., Zhang, S., et al.: Data augmentation for deep learning of judgment documents. In: International Conference on Intelligent Science and Big Data Engineering, pp. 232–242. Springer, Cham (2019)
Li, K., Chen, C., Quan, X., et al.: Conditional Augmentation for Aspect Term Extraction via Masked Sequence-to-Sequence Generation. arXiv preprint arXiv (2020)
Guo, H., Mao, Y., Zhang, R.: Augmenting data with mixup for sentence classification: an empirical study. arXiv preprint arXiv (2019)
Jans, B., Bethard, S., Vulic, I., et al.: Skip n-grams and ranking functions for predicting script events. In: Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics, pp. 336–344. ACL Press, United States (2012)
Granroth-Wilding, M., Clark, S.: What happens next? Event prediction using a compositional neural network model. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 2727–2733. AAAI Press, Palo Alto (2016)
Pichotta, K., Mooney, R.: Learning statistical scripts with LSTM recurrent neural networks. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 2800–2806. AAAI Press, Palo Alto (2016)
Lv, S., Qian, W., Huang, L., et al.: Sam-net: integrating event-level and chain-level attentions to predict what happens next. In: Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence and Thirty-First Innovative Applications of Artificial Intelligence Conference and Ninth AAAI Symposium on Educational Advances in Artificial Intelligence, pp. 6802–6809. AAAI Press, Palo Alto (2019)
Li, Z., Ding, X., Liu, T.: Constructing narrative event evolutionary graph for script event prediction. In: Proceedings of the 27th International Joint Conference on Artificial Intelligence, pp. 4201–4207. AAAI Press, Palo Alto (2018)
Wang, Z., Zhang, Y., Chang, C.: Integrating order information and event relation for script event prediction. In: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pp. 57–67. ACL Press, Copenhagen (2017)
Wang, L., Yue, J., Guo, S., et al.: Multi-level connection enhanced representation learning for script event prediction. In: Proceedings of the Web Conference 2021, pp. 3524–3533. ACM Press, New York (2021)
Balasubramanian, N., Soderland, S., Etzioni, O.: Generating Coherent Event Schemas at Scale. ACL Press, Seattle (2013)
Acknowledgements
The authors would like to thank the anonymous reviewers for the help comments. This work was supported by the National University of Defense Technology Research Project ZK20-46, the Young Elite Scientists Sponsorship Program (2021-JCJQ-QT-050), the National Natural Science Foundation of China under Grants 61972207, U1836208, U1836110, and 61672290, and the China Postdoctoral Science Foundation funded project (2021MD703983).
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
Liu, Y. et al. (2023). Improving Event Representation for Script Event Prediction via Data Augmentation and Integration. In: Liu, F., Duan, N., Xu, Q., Hong, Y. (eds) Natural Language Processing and Chinese Computing. NLPCC 2023. Lecture Notes in Computer Science(), vol 14303. Springer, Cham. https://doi.org/10.1007/978-3-031-44696-2_52
Download citation
DOI: https://doi.org/10.1007/978-3-031-44696-2_52
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-44695-5
Online ISBN: 978-3-031-44696-2
eBook Packages: Computer ScienceComputer Science (R0)