A Structured Learning Approach to Temporal Relation Extraction

Qiang Ning, Zhili Feng, Dan Roth


Abstract
Identifying temporal relations between events is an essential step towards natural language understanding. However, the temporal relation between two events in a story depends on, and is often dictated by, relations among other events. Consequently, effectively identifying temporal relations between events is a challenging problem even for human annotators. This paper suggests that it is important to take these dependencies into account while learning to identify these relations and proposes a structured learning approach to address this challenge. As a byproduct, this provides a new perspective on handling missing relations, a known issue that hurts existing methods. As we show, the proposed approach results in significant improvements on the two commonly used data sets for this problem.
Anthology ID:
D17-1108
Volume:
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
Month:
September
Year:
2017
Address:
Copenhagen, Denmark
Editors:
Martha Palmer, Rebecca Hwa, Sebastian Riedel
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
1027–1037
Language:
URL:
https://aclanthology.org/D17-1108
DOI:
10.18653/v1/D17-1108
Bibkey:
Cite (ACL):
Qiang Ning, Zhili Feng, and Dan Roth. 2017. A Structured Learning Approach to Temporal Relation Extraction. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 1027–1037, Copenhagen, Denmark. Association for Computational Linguistics.
Cite (Informal):
A Structured Learning Approach to Temporal Relation Extraction (Ning et al., EMNLP 2017)
Copy Citation:
PDF:
https://aclanthology.org/D17-1108.pdf
Video:
 https://aclanthology.org/D17-1108.mp4
Data
TempEval-3