Identify Event Causality with Knowledge and Analogy
Sifan Wu, Ruihui Zhao, Yefeng Zheng, Jian Pei, Bang Liu
Abstract
Event causality identification (ECI) aims to identify the causal relationship between events, which plays a crucial role in deep text understanding. Due to the diversity of real-world causality events and difficulty in obtaining sufficient training data, existing ECI approaches have poor generalizability and struggle to identify the relation between seldom seen events. In this paper, we propose to utilize both external knowledge and internal analogy to improve ECI. On the one hand, we utilize a commonsense knowledge graph called ConceptNet to enrich the description of an event sample and reveal the commonalities or associations between different events. On the other hand, we retrieve similar events as analogy exam- ples and glean useful experiences from such analogous neigh- bors to better identify the relationship between a new event pair. By better understanding different events through exter- nal knowledge and making an analogy with similar events, we can alleviate the data sparsity issue and improve model gener- alizability. Extensive evaluations on two benchmark datasets show that our model outperforms other baseline methods by around 18% on the F1-value on average
BibTeX
@article{Wu_Zhao_Zheng_Pei_Liu_2023, title={Identify Event Causality with Knowledge and Analogy}, volume={37}, url={https://ojs.aaai.org/index.php/AAAI/article/view/26610}, DOI={10.1609/aaai.v37i11.26610}, abstractNote={Event causality identification (ECI) aims to identify the
causal relationship between events, which plays a crucial role
in deep text understanding. Due to the diversity of real-world
causality events and difficulty in obtaining sufficient training
data, existing ECI approaches have poor generalizability and
struggle to identify the relation between seldom seen events.
In this paper, we propose to utilize both external knowledge
and internal analogy to improve ECI. On the one hand, we
utilize a commonsense knowledge graph called ConceptNet
to enrich the description of an event sample and reveal the
commonalities or associations between different events. On
the other hand, we retrieve similar events as analogy exam-
ples and glean useful experiences from such analogous neigh-
bors to better identify the relationship between a new event
pair. By better understanding different events through exter-
nal knowledge and making an analogy with similar events, we
can alleviate the data sparsity issue and improve model gener-
alizability. Extensive evaluations on two benchmark datasets
show that our model outperforms other baseline methods by
around 18% on the F1-value on average}, number={11}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Wu, Sifan and Zhao, Ruihui and Zheng, Yefeng and Pei, Jian and Liu, Bang}, year={2023}, month={Jun.}, pages={13745-13753} }