TY - GEN
T1 - The Future is not One-dimensional
T2 - 2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021
AU - Li, Manling
AU - Li, Sha
AU - Wang, Zhenhailong
AU - Huang, Lifu
AU - Cho, Kyunghyun
AU - Ji, Heng
AU - Han, Jiawei
AU - Voss, Clare
N1 - Funding Information:
This research is based upon work supported by U.S. DARPA KAIROS Program Nos. FA8750-19-2-1004 and Air Force No. FA8650-17-C-7715. The views and conclusions contained herein are those of the authors and should not be interpreted as necessarily representing the official policies, either expressed or implied, of DARPA, or the U.S. Government. The U.S. Government is authorized to reproduce and distribute reprints for governmental purposes notwithstanding any copyright annotation therein.
Publisher Copyright:
© 2021 Association for Computational Linguistics
PY - 2021
Y1 - 2021
N2 - 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 23.8% on HITS@1.
AB - 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 23.8% on HITS@1.
UR - http://www.scopus.com/inward/record.url?scp=85127372166&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85127372166&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85127372166
T3 - EMNLP 2021 - 2021 Conference on Empirical Methods in Natural Language Processing, Proceedings
SP - 5203
EP - 5215
BT - EMNLP 2021 - 2021 Conference on Empirical Methods in Natural Language Processing, Proceedings
PB - Association for Computational Linguistics (ACL)
Y2 - 7 November 2021 through 11 November 2021
ER -