The Future is not One-dimensional: Complex Event Schema Induction by Graph Modeling for Event Prediction
Manling Li, Sha Li, Zhenhailong Wang, Lifu Huang, Kyunghyun Cho, Heng Ji, Jiawei Han, Clare Voss
Abstract
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.- Anthology ID:
- 2021.emnlp-main.422
- Volume:
- Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
- Month:
- November
- Year:
- 2021
- Address:
- Online and Punta Cana, Dominican Republic
- Editors:
- Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 5203–5215
- Language:
- URL:
- https://aclanthology.org/2021.emnlp-main.422
- DOI:
- 10.18653/v1/2021.emnlp-main.422
- Cite (ACL):
- Manling Li, Sha Li, Zhenhailong Wang, Lifu Huang, Kyunghyun Cho, Heng Ji, Jiawei Han, and Clare Voss. 2021. The Future is not One-dimensional: Complex Event Schema Induction by Graph Modeling for Event Prediction. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 5203–5215, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
- Cite (Informal):
- The Future is not One-dimensional: Complex Event Schema Induction by Graph Modeling for Event Prediction (Li et al., EMNLP 2021)
- PDF:
- https://preview.aclanthology.org/proper-vol2-ingestion/2021.emnlp-main.422.pdf
- Code
- limanling/temporal-graph-schema