Encoding emotional information for sequence-to-sequence response generation

This paper introduces an alternative approach on embedding emotional information at the encoder stage of a sequence-to-sequence based emotional response generation. It explores different positioning and styles of the embedding, which represent associations of emotion with specific words or the whole sentence. The experiment was set up with standard dataset as well as dataset annotated with emotional classifiers. Preliminary results showed that this new approach should better represent sentence level emotional and work well with standard Recurrent Neural network (RNN) with Long Short Term Memory (LSTM) architecture.