Intent Detection for Spoken Language Understanding Using a Deep Ensemble Model

One of the significant task in spoken language understanding ( SLU) is intent detection. In this paper, we propose a deep learning based ensemble model for intent detection. The outputs of different deep learning architectures such as convolutional neural network ( CNN) and variants of recurrent neural networks ( RNN) like long short term memory ( LSTM) and gated recurrent units ( GRU) are combined together using a multi-layer perceptron ( MLP). The classifiers are trained using a combined word embedding representation obtained from both Word2Vec and Glove. Our experiments on the benchmark ATIS dataset show state-of-the-art performance for intent detection.