Virtual conversational agents, or Chatbots, are quickly becoming a ubiquitous element of human-computer interaction as well as customer-business communications. Modern Natural Language Processing (NLP) and Natural Language Generation (NLG) techniques often utilize Machine Learning methodology in order to train a Chatbot on datasets of English language and dialogue, allowing what seems like natural English responses to emerge from the agent. This façade of understanding does not allow for reasoning to take place within the agent.
We propose a framework for construction Chatbot capable of human-like casual conversation which integrates rule-based reasoning and human conversational behaviors into both the NLP and NLG aspects of the agent. This framework operates using an information-state-based dialogue manager called Forward Looking, Reward Seeking (FLoReS). Chatbot characters written using this framework possess conversational goals and behaviors as defined by the author, allowing for these Chatbots to possess unique personalities and distinct utterances. Integrated into this framework is an explicit representation of memory and knowledge, also defined by the Chatbot author, which allows for the Chatbot to “remember” information from previous interactions with a user. Chatbots written with human conversational abilities will provide a more natural means of interaction with a user.
