Learning towards conversational AI: A survey

Abstract

Recent years have witnessed a surge of interest in the field of open-domain dialogue. Thanks to the rapid development of social media, large dialogue corpus from the Internet builds up a fundamental premise for data-driven dialogue model. The breakthrough in neural network also brings new ideas to researchers in AI and NLP. A great number of new techniques and methods therefore came into being. In this paper, we review some of the most representative works in recent years and divide existing prevailing frameworks for a dialogue model into three categories. We further analyze the trend of development for open-domain dialogue and summarize the goal of an open-domain dialogue system in two aspects, informative and controllable. The methods we review in this paper are selected according to our unique perspectives and by no means complete. Rather, we hope this servery could benefit NLP community for future research in open-domain dialogue.

Keywords

• Human-machine conversation
• Response generation
• Informativeness dialogue
• Controllable dialogue