Integrating Scene Image and Conversational Text to Develop Human–Machine Dialogue

Abstract

In recent years, it has become a trend to build social dialogue systems to achieve human–robot interaction. While current conversational systems mostly focus on the dialogue utterances, visual context also plays an important role in determining the relevance of the system responses to the dialogue. In this study, we develop an integrated approach to investigate how to achieve such a visual-language task. Our approach takes both scene images and dialogue utterances into account and trains a neural model to generate machine responses of natural language. We have conducted a series of experiments to evaluate the presented approach, and the results confirm its usefulness and effectiveness.