计算机工程与应用2019，Vol.55Issue(12)：145-148,161,5.DOI:10.3778/j.issn.1002-8331.1803-0231
引入外部记忆的循环神经网络的口语理解
Spoken Language Understanding Method Based on Recurrent Neural Network with Persistent Memory
摘要
Abstract
Recurrent Neural Network(RNN)has increasingly shown its advantages in the Spoken Language Understanding (SLU)task. However, because of the problem of gradient disappearance and gradient explosion, the storage capacity of simple recurrent neural network is limited. A RNN that uses external memory is proposed to improve memory. Experi-ments are carried out on the ATIS data set and compared with other publicly reported models. The results show that, in oral comprehension tasks, the RNN introduced external memory has significantly improved accuracy, recall rate and F1-score, which is superior to traditional recurrent neural network and its variant structure.关键词
口语理解/循环神经网络/长短时记忆网络/神经图灵机Key words
Spoken Language Understanding(SLU)/ Recurrent Neural Network(RNN)/ Long Short Term Memory (LSTM)network/ neural turing machine分类
信息技术与安全科学引用本文复制引用
许莹莹,黄浩..引入外部记忆的循环神经网络的口语理解[J].计算机工程与应用,2019,55(12):145-148,161,5.基金项目
国家自然科学基金(No.61365005,No.61663044,No.61761041) （No.61365005,No.61663044,No.61761041）
新疆大学博士科研启动基金(No.BS160239). （No.BS160239）
