一种基于深度神经网络的句法要素识别方法

为改进传统特征方法很难获取中文句子中结构信息的问题，提出一种基于深度神经网络的句法要素识别模型。采用Bi-LSTM网络从原始数据中自动抽取句子中的结构信息和语义信息，利用Attention机制自动计算抽象语义特征的分类权重，通过CRF层对输出标签进行约束，输出最优的标注序列。经过对比验证，该模型能有效识别句子中的句法要素，在标注数据集上F₁达到84.85%。

A syntactic element recognition method based on deep neural network

It was difficult to obtain structural information in Chinese sentences by the traditional feature method. To solve the problem, according to characteristics of Chinese sentence, a Bi-LSTM-Attention-CRF model was proposed based on deep neural network. A Bi-LSTM network was used to automatically extract structural information and semantic information from raw input sentences. Attention mechanism was adopted to weight abstract semantic features for classification. An optimized label sequence was output through the CRF layer. Comparing with other methods, our model could effectively identify syntactic elements in sentences. The performance reached to 84.85% in F₁ score in the evaluation data sets.