面向工艺文本的命名实体识别方法研究

Named Entity Recognition for Process Text

面向工艺文本中的命名实体,该文提出一种融入领域知识的神经网络命名实体识别方法,旨在对零件、工程图纸、参考标准、属性等12类命名实体进行识别。该方法针对工艺实体的特点,利用领域词典及规则预识别出部分实体,形成预识别实体特征,将预识别实体特征加入CNN-BiLSTM-CRF神经网络模型,指导训练与预测。实验结果表明,该方法在工艺文本中能较好地完成命名实体识别任务,在提高词典及规则覆盖的实体识别效果的同时,还能够提高其他类实体的识别效果,通过加入预识别实体特征,使得F_(1)值从90.99%提升到93.03%,验证了该文方法的有效性。

This paper proposes,a method of identifying named entities based on neural network with domain knowledge to identify 12 types of process entities including parts,engineering drawings,reference standards and attributes.According to the characteristics of process entities,this method uses domain dictionaries and rules to pre-identify candidate entities to form pre-recognition features,which are then fed to the CNN-BiLSTM-CRF neural network model.The experimental results show that,by adding pre-recognition entity features,the F1 value is increased from 90.99%to 93.03%.