循环神经网络中基于特征融合的口语理解

Feature fusion based recurrent neural network for spoken language understanding

口语理解(SLU)性能的好坏对口语对话系统有着至关重要的作用。在对基本循环神经网络及其变体长短时记忆(LSTM)网络和门限循环单元(GRU)网络结构分析的基础上,提出一种特征融合的循环神经网络结构。该结构首先把输入送到隐含层训练得到特征表示;然后该特征信息与源输入及历史输出信息一起送入另一隐含层训练;最后送进输出层得出结果。对上述不同的循环神经网络的结构及提出的模型在ATIS数据库上进行口语理解实验。结果表明,提出的特征融合的循环神经网络结构的性能要优于传统循环神经网络及其变体结构。

The performance of spoken language understanding(SLU)is of fundamental importance to a spoken language dialogue system.A feature fusion based recurrent neural network structure is proposed on the basis of analyzing the structures of basic recurrent neural network(RNN)and its variants of long short-term memory(LSTM)network and gated recurrent unit(GRU)network.In the structure,the input is sent to the hidden layer and trained to obtain feature representation.The feature information,together with the source input and historical output information,is sent to another hidden layer for training,and then sent to the output layer to obtain results.An SLU experiment was carried out on the ATIS database using the above differ?ent recurrent neural network structures and proposed models.The results show that the performance of the feature fusion based recurrent neural network structure is better than that of the conventional recurrent neural network and its variants.