Neural-based Context Representation Learning for Dialog Act\n Classification

We explore context representation learning methods in neural-based models for\ndialog act classification. We propose and compare extensively different methods\nwhich combine recurrent neural network architectures and attention mechanisms\n(AMs) at different context levels. Our experimental results on two benchmark\ndatasets show consistent improvements compared to the models without contextual\ninformation and reveal that the most suitable AM in the architecture depends on\nthe nature of the dataset.\n