Abstract:

Aiming at the common non-linear relationship between characters in languages， in order to capture richer semantic features， a Named Entity Recognition （NER） method based on Graph Convolutional Network （GCN） and self-attention mechanism was proposed. Firstly， with the help of the effective extraction ability of character features of deep learning methods， the GCN was used to learn the global semantic features between characters， and the Bidirectional Long Short-Term Memory network （BiLSTM） was used to extract the context-dependent features of the characters. Secondly， the above features were fused and their internal importance was calculated by introducing a self-attention mechanism. Finally， the Conditional Random Field （CRF） was used to decode the optimal coding sequence from the fused features， which was used as the result of entity recognition. Experimental results show that compared with the method that only uses BiLSTM or CRF， the proposed method has the recognition precision increased by 2.39% and 15.2% respectively on MicroSoft Research Asia （MSRA） dataset and Biomedical Natural Language Processing/Natural Language Processing in Biomedical Applications （BioNLP/NLPBA） 2004 dataset， indicating that this method has good sequence labeling capability on both Chinese and English datasets， and has strong generalization capability.

Key words: Named Entity Recognition （NER）, sequence labeling, self-attention mechanism, Graph Convolution Network （GCN）, Bidirectional Long Short-Term Memory network （BiLSTM）

摘要：

针对语言普遍存在的字符间非线性关系，为捕获更丰富的语义特征，提出了一种基于图卷积神经网络（GCN）和自注意力机制的命名实体识别（NER）方法。首先，借助深度学习方法有效提取字符特征的能力，采用GCN学习字符间的全局语义特征，并且采用双向长短时记忆网络（BiLSTM）提取字符的上下文依赖特征；其次，融合以上特征并引入自注意力机制计算其内部重要度；最后，使用条件随机场（CRF）从融合特征中解码出最优的编码序列，并以此作为实体识别的结果。实验结果表明，与单一采用BiLSTM和CRF的方法相比，所提方法在微软亚洲研究院（MSRA）数据集和BioNLP/NLPBA 2004数据集上的精确率分别至少提高了2.39%和15.2%。可见该方法在中文和英文数据集上都具备良好的序列标注能力，且泛化能力较强。

关键词: 命名实体识别, 序列标注, 自注意力机制, 图卷积网络, 双向长短时记忆网络