%0 Conference Proceedings %T The Future is not One-dimensional: Complex Event Schema Induction by Graph Modeling for Event Prediction %A Li, Manling %A Li, Sha %A Wang, Zhenhailong %A Huang, Lifu %A Cho, Kyunghyun %A Ji, Heng %A Han, Jiawei %A Voss, Clare %Y Moens, Marie-Francine %Y Huang, Xuanjing %Y Specia, Lucia %Y Yih, Scott Wen-tau %S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing %D 2021 %8 November %I Association for Computational Linguistics %C Online and Punta Cana, Dominican Republic %F li-etal-2021-future %X Event schemas encode knowledge of stereotypical structures of events and their connections. As events unfold, schemas are crucial to act as a scaffolding. Previous work on event schema induction focuses either on atomic events or linear temporal event sequences, ignoring the interplay between events via arguments and argument relations. We introduce a new concept of Temporal Complex Event Schema: a graph-based schema representation that encompasses events, arguments, temporal connections and argument relations. In addition, we propose a Temporal Event Graph Model that predicts event instances following the temporal complex event schema. To build and evaluate such schemas, we release a new schema learning corpus containing 6,399 documents accompanied with event graphs, and we have manually constructed gold-standard schemas. Intrinsic evaluations by schema matching and instance graph perplexity, prove the superior quality of our probabilistic graph schema library compared to linear representations. Extrinsic evaluation on schema-guided future event prediction further demonstrates the predictive power of our event graph model, significantly outperforming human schemas and baselines by more than 17.8% on HITS@1. %R 10.18653/v1/2021.emnlp-main.422 %U https://aclanthology.org/2021.emnlp-main.422 %U https://doi.org/10.18653/v1/2021.emnlp-main.422 %P 5203-5215