基于RNN弱监督网络的英语语义分析技术研究

Research on English semantic analysis technology based on RNN weak supervised network

英语语义的精准识别与分析在计算机与人工智能技术应用领域具有重要的意义,传统的文本分析技术实时性差、分析精确度与效率低,文中基于神经网络设计了一套英语语义分析方法。为获取英语文本中的所有信息,选取递归神经网络识别单词模型,设计了包含输入层、隐藏层与输出层的RNN网络。为识别不同句式的英语文本,选取长短时记忆网络提取文本的有用信息,通过实验选取误差值最小的识别网络。分析实验数据测试结果可知,与传统的DiSan等语句分析方法相比,该LSTM-RNN网络的相关性能准确率高达94.5%,且模型占用硬件资源少,具有较优的应用前景。

Accurate recognition and analysis of English semantics is of great significance in the application of computer and artificial intelligence technology.Traditional text analysis technology has poor real-time performance,analysis accuracy and efficiency.Based on neural network,a set of semantic analysis methods is designed.In order to obtain all the information in English text,a RNN network including input layer,hidden layer and output layer is designed by selecting recurrent neural network to recognize the word model.In order to recognize English texts with different sentence patterns,the long term and short-term memory networks are selected to extract useful information from texts,and the recognition networks with the smallest error value are selected through experiments.According to the test results of the experimental data,compared with the traditional sentence analysis methods such as DiSan,the performance accuracy of the LSTM-RNN network is up to 94.5%,and the model occupies less hardware resources,so it has a good application prospect.