Knowledge-Based Systems ( IF 7.2 ) Pub Date : 2020-01-10 , DOI: 10.1016/j.knosys.2020.105488 Qing Li , Lili Li , Weinan Wang , Qi Li , Jiang Zhong
Semantic relation extraction between entity pairs is a crucial task in information extraction from text. In this paper, we propose a new pre-trained network architecture for this task, and it is called the XM-CNN. The XM-CNN utilizes word embedding and position embedding information. It is designed to reinforce the contextual output from the MT-DNN pre-trained model. Our model effectively utilized an entity-aware attention mechanisms to detected the features and also adopts and applies more relation-specific pooling attention mechanisms applied to it. The experimental results show that the XM-CNN achieves state-of-the-art results on the SemEval-2010 task 8, and a thorough evaluation of the method is conducted.
中文翻译:
通过预训练的CNN进行语义关系提取的全面探索
实体对之间的语义关系提取是从文本中提取信息的关键任务。在本文中,我们针对此任务提出了一种新的预训练网络架构,称为XM-CNN。XM-CNN利用单词嵌入和位置嵌入信息。它旨在增强MT-DNN的上下文输出预训练模型。我们的模型有效地利用了实体感知的注意力机制来检测特征,并且采用并应用了更多针对关系的池化注意力机制。实验结果表明,XM-CNN在SemEval-2010任务8上取得了最先进的结果,并对该方法进行了全面评估。