A Weakly Supervised Approach to Train Temporal Relation Classifiers and Acquire Regular Event Pairs Simultaneously

Wenlin Yao, Saipravallika Nettyam, Ruihong Huang


Abstract
Capabilities of detecting temporal and causal relations between two events can benefit many applications. Most of existing temporal relation classifiers were trained in a supervised manner. Instead, we explore the observation that regular event pairs show a consistent temporal relation despite of their various contexts and these rich contexts can be used to train a contextual temporal relation classifier, which can further recognize new temporal relation contexts and identify new regular event pairs. We focus on detecting after and before temporal relations and design a weakly supervised learning approach that extracts thousands of regular event pairs and learns a contextual temporal relation classifier simultaneously. Evaluation shows that the acquired regular event pairs are of high quality and contain rich commonsense knowledge and domain specific knowledge. In addition, the weakly supervised trained temporal relation classifier achieves comparable performance with the state-of-the-art supervised systems.
Anthology ID:
R17-1103
Volume:
Proceedings of the International Conference Recent Advances in Natural Language Processing, RANLP 2017
Month:
September
Year:
2017
Address:
Varna, Bulgaria
Editors:
Ruslan Mitkov, Galia Angelova
Venue:
RANLP
SIG:
Publisher:
INCOMA Ltd.
Note:
Pages:
803–812
Language:
URL:
https://doi.org/10.26615/978-954-452-049-6_103
DOI:
10.26615/978-954-452-049-6_103
Bibkey:
Cite (ACL):
Wenlin Yao, Saipravallika Nettyam, and Ruihong Huang. 2017. A Weakly Supervised Approach to Train Temporal Relation Classifiers and Acquire Regular Event Pairs Simultaneously. In Proceedings of the International Conference Recent Advances in Natural Language Processing, RANLP 2017, pages 803–812, Varna, Bulgaria. INCOMA Ltd..
Cite (Informal):
A Weakly Supervised Approach to Train Temporal Relation Classifiers and Acquire Regular Event Pairs Simultaneously (Yao et al., RANLP 2017)
Copy Citation:
PDF:
https://doi.org/10.26615/978-954-452-049-6_103