Utilizing Relative Event Time to Enhance Event-Event Temporal Relation Extraction

Haoyang Wen, Heng Ji


Abstract
Event time is one of the most important features for event-event temporal relation extraction. However, explicit event time information in text is sparse. For example, only about 20% of event mentions in TimeBank-Dense have event-time links. In this paper, we propose a joint model for event-event temporal relation classification and an auxiliary task, relative event time prediction, which predicts the event time as real numbers. We adopt the Stack-Propagation framework to incorporate predicted relative event time for temporal relation classification and keep the differentiability. Our experiments on MATRES dataset show that our model can significantly improve the RoBERTa-based baseline and achieve state-of-the-art performance.
Anthology ID:
2021.emnlp-main.815
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
10431–10437
Language:
URL:
https://aclanthology.org/2021.emnlp-main.815
DOI:
10.18653/v1/2021.emnlp-main.815
Bibkey:
Cite (ACL):
Haoyang Wen and Heng Ji. 2021. Utilizing Relative Event Time to Enhance Event-Event Temporal Relation Extraction. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 10431–10437, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Utilizing Relative Event Time to Enhance Event-Event Temporal Relation Extraction (Wen & Ji, EMNLP 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/update-css-js/2021.emnlp-main.815.pdf
Code
 wenhycs/emnlp2021-utilizing-relative-event-time-to-enhance-event-event-temporal-relation-extraction