Hybrid Code Networks using a convolutional neural network as an input layer achieves higher turn accuracy
This is an incremental improvement for conversational AI systems, specifically targeting dialogue managers.
The authors tackled dialogue management by enhancing Hybrid Code Networks with a convolutional neural network input layer, achieving improved turn accuracy on Dialogue bAbI Task 6 and Alquist Conversational Dataset.
The dialogue management is a task of conversational artificial intelligence. The goal of the dialogue manager is to select the appropriate response to the conversational partner conditioned by the input message and recent dialogue state. Hybrid Code Networks is one of the models of dialogue managers, which uses an average of word embeddings and bag-of-words as input features. We perform experiments on Dialogue bAbI Task 6 and Alquist Conversational Dataset. The experiments show that the convolutional neural network used as an input layer of the Hybrid Code Network improves the model's turn accuracy.