一种面向自然语言问题的命名实体识别模型

A Named Entity Recognition model for problems in natural language

在诸如电力客户问题等此类专业技术领域的自然语言问题命名实体识别任务中,由于专业性及用语的地域性导致难以实现大规模标注数据。而采用传统基于有监督学习模型的命名实体识别方法,则较易陷入过拟合。针对上述问题,文中对关系网络中的嵌入模块和关系模块及样本采样、元训练集构建等方面进行了面向命名实体识别任务特点的设计,提出了一种基于关系网络小样本学习方法的实体识别模型。在电力客户问题实体识别数据集上的实验结果表明,该模型的F1等重要指标比常用的有监督识别模型提高了大约10%~40%。

In the Named Entity Recognition task of natural language problems in such fields as power customer problems,the specialty and regional language make it difficult to label data on a large scale,and the traditional supervised learning model is easy to fall into over fitting.To solve this problem,this paper designs the characteristics of Named Entity Recognition task from the aspects of embedding module and relationship module,sample sampling and meta training set construction in the relational network framework of small sample learning,and proposes an entity recognition model of small sample learning method based on relational network.Experiments on the entity recognition data set of power customer problems show that the model is 10%~40%higher than the commonly used supervised recognition model in important indexes such as F1.