TIMERS: Document-level Temporal Relation Extraction

Puneet Mathur, Rajiv Jain, Franck Dernoncourt, Vlad Morariu, Quan Hung Tran, Dinesh Manocha


Abstract
We present TIMERS - a TIME, Rhetorical and Syntactic-aware model for document-level temporal relation classification in the English language. Our proposed method leverages rhetorical discourse features and temporal arguments from semantic role labels, in addition to traditional local syntactic features, trained through a Gated Relational-GCN. Extensive experiments show that the proposed model outperforms previous methods by 5-18% on the TDDiscourse, TimeBank-Dense, and MATRES datasets due to our discourse-level modeling.
Anthology ID:
2021.acl-short.67
Volume:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
Month:
August
Year:
2021
Address:
Online
Editors:
Chengqing Zong, Fei Xia, Wenjie Li, Roberto Navigli
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
524–533
Language:
URL:
https://aclanthology.org/2021.acl-short.67
DOI:
10.18653/v1/2021.acl-short.67
Bibkey:
Cite (ACL):
Puneet Mathur, Rajiv Jain, Franck Dernoncourt, Vlad Morariu, Quan Hung Tran, and Dinesh Manocha. 2021. TIMERS: Document-level Temporal Relation Extraction. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 524–533, Online. Association for Computational Linguistics.
Cite (Informal):
TIMERS: Document-level Temporal Relation Extraction (Mathur et al., ACL-IJCNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.acl-short.67.pdf
Video:
 https://aclanthology.org/2021.acl-short.67.mp4
Data
MATRES