Virtual conversational agents, or Chatbots, are quickly becoming a ubiquitous element of human-computer interaction, customer-business communications, and entertainment. Modern Natural Language Processing (NLP) and Natural Language Generation (NLG) techniques often utilize Machine Learning methodology to train a Chatbot on datasets of English language and dialogue, allowing what seem like natural English responses to emerge from the agent. However, this façade of understanding by the Chatbot is often mistaken for hard-coded reasoning taking place within the agent.
This project proposes a framework for construction of Chatbot characters 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 created using this framework possess conversational goals and behaviors as defined by the author, allowing for these characters 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 characters created with human conversational abilities can provide a more natural means of interaction with a user. These interactions contribute to improved human-computer communication and consumer interaction, and provide alternative and unexplored avenues for storytelling through character dialogue and behavioral design. The paper portion of this project examines background work in conversational agents as well as the motivations and reasoning behind the framework presented. The interactive portion of this project will allow a user to converse with a Chatbot character created using this framework.
