计算机工程与应用2019，Vol.55Issue(18)：155-160,6.DOI:10.3778/j.issn.1002-8331.1808-0256
口语理解中改进循环神经网络的应用
Modified Recurrent Neural Networks in Spoken Language Understanding
摘要
Abstract
The improvement of Spoken Language Understanding(SLU)plays an important role in spoken dialogue sys-tem. Recurrent neural network and its variants are used to improve performance of SLU. The modified recurrent neural network algorithm is proposed to enhance the SLU, which adds the memory of longer historical information and has fewer parameters. This method can efficiently obtain feature information that not only improves the precision and F1 but also cut down experimental period. The experimental results on the ATIS corpus verify the effectiveness and reliability of the proposed algorithm.关键词
循环神经网络(RNN)/长短时记忆网络(LSTM)/门限循环单元(GRU)/口语理解(SLU)/改进循环神经网络(M-RNN)Key words
Recurrent Neural Network(RNN)/Long Short-Term Memory(LSTM)/Gated Recurrent Uni(t GRU)/Spo-ken Language Understanding(SLU)/Modified Recurrent Neural Networks(M-RNN)分类
信息技术与安全科学引用本文复制引用
张晶晶,黄浩,胡英,吾守尔·斯拉木..口语理解中改进循环神经网络的应用[J].计算机工程与应用,2019,55(18):155-160,6.基金项目
国家自然科学基金(No.61663044,No.61761041) （No.61663044,No.61761041）
国家重点研发计划项目(No.2017YFB1402101). （No.2017YFB1402101）
