计算机科学
推论
事件(粒子物理)
任务(项目管理)
信息抽取
关系抽取
人工智能
计算
萃取(化学)
机器学习
模式识别(心理学)
数据挖掘
算法
物理
管理
量子力学
经济
化学
色谱法
作者
Guanqiu Qin,Nankai Lin,Menglan Shen,Qifeng Bai,Dong Zhou,Aimin Yang
标识
DOI:10.1016/j.eswa.2023.122516
摘要
Document-level event extraction (DEE) is a branch of information extraction task that is valuable but difficult at present. To effectively implement DEE, previous works with better performance are often accompanied by larger parameters and computation. In this paper, we propose a novel framework based on global information enhancement and subgraph-level weakly contrastive learning, which bring better performance at lower extra computing costs. We verify the effectiveness of our method in a lightweight DEE model. The experimental results indicate that our proposed method outperforms other approaches in terms of the F1 score for both overall event extraction evaluation and single event extraction. In the inference phase, our model uses only 25% of the GPU memory required by the optimal model and maintains the advantage of 6.4 times faster inference speed.
科研通智能强力驱动
Strongly Powered by AbleSci AI