关系分类是自然语言处理领域的重要语义处理任务。将卷积神经网络和递归神经网络与注意机制相结合的深度学习技术一直是主流和最先进的方法。基于递归神经网络的LSTM模型通过门控动态地控制权值,能够较好地提取时间序列中的上下文状态信息,有效地解决了递归神经网络长期以来存在的问题。预先训练好的模型BERT在许多自然语言处理任务中也取得了优异的效果。本文提出了一种基于注意机制的BERT和LSTM多通道字符关系分类模型。通过注意机制,将两个模型的语义信息进行融合,得到最终的分类结果。利用该模型对文本进行处理,可以对字符之间的关系进行提取和分类,最终得到本文所包含的字符之间的关系。实验结果表明,在SemEval-2010任务8数据集和COAE-2016 - Task3数据集上,该方法的性能优于以往的深度学习模型。

Relation classification is an important semantic processing task in the field of natural language processing. The deep learning technology, which combines Convolutional Neural Network and Recurrent Neural Network with attention mechanism, has always been the mainstream and state-of-art method. The LSTM model based on recurrent neural network dynamically controls the weight by gating, which can better extract the context state information in time series and effectively solve the long-standing problem of recurrent neural network. The pre-trained model BERT has also achieved excellent results in many natural language processing tasks. This paper proposes a multi-channel character relationship classification model of BERT and LSTM based on attention mechanism. Through the attention mechanism, the semantic information of the two models is fused to get the final classification result. Using this model to process the text, we can extract and classify the relationship between the characters, and finally get the relationship between the characters included in this paper. Experimental results show that the proposed method performs better than the previous deep learning model on the SemEval-2010 task 8 dataset and the COAE-2016-Task3 dataset.