Event Time Extraction and Propagation via Graph Attention Networks

Haoyang Wen, Yanru Qu, Heng Ji, Qiang Ning, Jiawei Han, Avi Sil, Hanghang Tong, Dan Roth


Abstract
Grounding events into a precise timeline is important for natural language understanding but has received limited attention in recent work. This problem is challenging due to the inherent ambiguity of language and the requirement for information propagation over inter-related events. This paper first formulates this problem based on a 4-tuple temporal representation used in entity slot filling, which allows us to represent fuzzy time spans more conveniently. We then propose a graph attention network-based approach to propagate temporal information over document-level event graphs constructed by shared entity arguments and temporal relations. To better evaluate our approach, we present a challenging new benchmark on the ACE2005 corpus, where more than 78% of events do not have time spans mentioned explicitly in their local contexts. The proposed approach yields an absolute gain of 7.0% in match rate over contextualized embedding approaches, and 16.3% higher match rate compared to sentence-level manual event time argument annotation.
Anthology ID:
2021.naacl-main.6
Volume:
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
June
Year:
2021
Address:
Online
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
62–73
Language:
URL:
https://aclanthology.org/2021.naacl-main.6
DOI:
10.18653/v1/2021.naacl-main.6
Bibkey:
Cite (ACL):
Haoyang Wen, Yanru Qu, Heng Ji, Qiang Ning, Jiawei Han, Avi Sil, Hanghang Tong, and Dan Roth. 2021. Event Time Extraction and Propagation via Graph Attention Networks. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 62–73, Online. Association for Computational Linguistics.
Cite (Informal):
Event Time Extraction and Propagation via Graph Attention Networks (Wen et al., NAACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.naacl-main.6.pdf
Video:
 https://aclanthology.org/2021.naacl-main.6.mp4
Code
 wenhycs/naacl2021-event-time-extraction-and-propagation-via-graph-attention-networks