.png){kind=icon}
返回
Salient event detection via hypergraph convolutional network with cross-view self
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2024.128639.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Identifying the most dominant and central events in a document is critical for holistically understanding its important information. To measure the importance of an event, it is critical to understand its context: who is involved, where it happened, which other events it is related to, and what kind of relationship it has, among other factors. Although existing studies have achieved some accomplishments, they are still not fully effective for two main reasons: (1) They incorporate only the discrete global features of the document, which is insufficient for effectively capturing the contextual information of events; (2) They inadequately model the dependency relationships between events. According to previous research findings, it has been shown that hypergraphs effectively capture the global context (i.e., the document-level context) of long text. However, their potential for salient event detection has remained unexplored. To address this, we propose a novel framework called Salient Event Detection via Hypergraph Convolutional Network with Graph Self-supervised Learning (SEDGS). More specifically, we first construct two hypergraphs: one in the event argument view and another in the event view. We then propose a hypergraph convolutional network to model the event context and discourse relations between events. Moreover, to enhance hypergraph modeling and ensure consistency between argument-view and event-view event representations, we employ contrastive self-supervised learning (SSL) in our model training. Experimental results on a standard event salience dataset verify the superiority of SEDGS, advancing state-of-the-art models.
Keyword:
Salient event detection
Event representation
Graph neural network
Hypergraph learning
Self-supervised learning
期刊
IF:
6.5
论文数:
2.5W
被引数:
6.5W
机构
暂无机构信息
引用论文
Using CRISPR-Cas9 genome editing to enhance disease resistance in banana利用CRISPR-Cas9基因组编辑技术增强香蕉的抗病性.png)
CABI Reviews
CABI ReviewsIF0
PREAI
分享收藏Peripheral-photoinhibition-based direct laser writing with isotropic 30 nm feature size using a pseudo 3D hollow focus基于边缘光抑制效应的直接激光写入技术，使用伪3D空心焦点实现各向同性30 nm特征尺寸
PREAI
分享收藏
Efficient organic DSSC sensitizers bearing an electron-deficient pyrimidine as an effective π-spacer
PREAI
分享收藏
查看更多内容