KnowDis: Knowledge Enhanced Data Augmentation for Event Causality Detection via Distant Supervision

Xinyu Zuo, Yubo Chen, Kang Liu, Jun Zhao


Abstract
Modern models of event causality detection (ECD) are mainly based on supervised learning from small hand-labeled corpora. However, hand-labeled training data is expensive to produce, low coverage of causal expressions, and limited in size, which makes supervised methods hard to detect causal relations between events. To solve this data lacking problem, we investigate a data augmentation framework for ECD, dubbed as Knowledge Enhanced Distant Data Augmentation (KnowDis). Experimental results on two benchmark datasets EventStoryLine corpus and Causal-TimeBank show that 1) KnowDis can augment available training data assisted with the lexical and causal commonsense knowledge for ECD via distant supervision, and 2) our method outperforms previous methods by a large margin assisted with automatically labeled training data.
Anthology ID:
2020.coling-main.135
Volume:
Proceedings of the 28th International Conference on Computational Linguistics
Month:
December
Year:
2020
Address:
Barcelona, Spain (Online)
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
1544–1550
Language:
URL:
https://aclanthology.org/2020.coling-main.135
DOI:
10.18653/v1/2020.coling-main.135
Bibkey:
Cite (ACL):
Xinyu Zuo, Yubo Chen, Kang Liu, and Jun Zhao. 2020. KnowDis: Knowledge Enhanced Data Augmentation for Event Causality Detection via Distant Supervision. In Proceedings of the 28th International Conference on Computational Linguistics, pages 1544–1550, Barcelona, Spain (Online). International Committee on Computational Linguistics.
Cite (Informal):
KnowDis: Knowledge Enhanced Data Augmentation for Event Causality Detection via Distant Supervision (Zuo et al., COLING 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2020.coling-main.135.pdf
Data
COPA