Semantic Fusion Enhanced Event Detection via Multi-Graph Attention Network with Skip Connection

Wu, Gongqing; Lu, Zhenya; Zhuo, Xingrui; Bao, Xianyu; Wu, Xindong

doi:10.1109/tetci.2022.3229414

Search citation statements

Order By: Relevance

Paper Sections

Select...

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2024

Publication Types

Select...

Article2

Other1

Relationship

Self Cite0

Independent3

Authors

Journals

Cited by 3 publications

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Semantic-enhanced graph neural networks with global context representation

Qian,

Yin

2024

Mach Learn

View full text Add to dashboard Cite

Semantic-enhanced graph neural networks with global context representation

Qian,

Yin

2024

Mach Learn

View full text Add to dashboard Cite

Dual-channel Enhanced Graph Convolutional Network for Event Detection

Shen,

Ying,

Ding

et al. 2024

Proceedings of the 5th International Conference on Computer Information and Big Data Applications

View full text Add to dashboard Cite

AssocKD: An Association-Aware Knowledge Distillation Method for Document-Level Event Argument Extraction

Tan,

Hu,

Cao

et al. 2024

Mathematics

View full text Add to dashboard Cite

Event argument extraction is a crucial subtask of event extraction, which aims at extracting arguments that correspond to argument roles when given event types. The majority of current document-level event argument extraction works focus on extracting information for only one event at a time without considering the association among events; this is known as document-level single-event extraction. However, the interrelationship among arguments can yield mutual gains in their extraction. Therefore, in this paper, we propose AssocKD, an Association-aware Knowledge Distillation Method for Document-level Event Argument Extraction, which enables the enhancement of document-level multi-event extraction with event association knowledge. Firstly, we introduce an association-aware training task to extract unknown arguments with the given privileged knowledge of relevant arguments, obtaining an association-aware model that can construct both intra-event and inter-event relationships. Secondly, we adopt multi-teacher knowledge distillation to transfer such event association knowledge from the association-aware teacher models to the event argument extraction student model. Our proposed method, AssocKD, is capable of explicitly modeling and efficiently leveraging event association to enhance the extraction of multi-event arguments at the document level. We conduct experiments on RAMS and WIKIEVENTS datasets and observe a significant improvement, thus demonstrating the effectiveness of our method.

show abstract

Semantic Fusion Enhanced Event Detection via Multi-Graph Attention Network with Skip Connection

Cited by 3 publications

References 35 publications

Semantic-enhanced graph neural networks with global context representation

Semantic-enhanced graph neural networks with global context representation

Dual-channel Enhanced Graph Convolutional Network for Event Detection

AssocKD: An Association-Aware Knowledge Distillation Method for Document-Level Event Argument Extraction

Contact Info

Product

Resources

About