Hybrid Code Networks using a convolutional neural network as an input layer achieves higher turn accuracy

TL;DR

This paper demonstrates that integrating a convolutional neural network as an input layer in Hybrid Code Networks enhances turn accuracy in dialogue management tasks, validated on Dialogue bAbI and Alquist datasets.

Contribution

The study introduces a convolutional neural network as an input layer in Hybrid Code Networks, improving dialogue turn accuracy over traditional input features.

Findings

Convolutional input layer increases turn accuracy.

Improved performance on Dialogue bAbI and Alquist datasets.

Hybrid Code Networks benefit from CNN-based inputs.

Abstract

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.