Author: Jeremy Lyle Brown

I'm Jeremy Brown and I'm a student at Macaulay Honors College at Baruch College, majoring in Cognitive Science & Computers as well as Interactive Storytelling through CUNY Baccalaureate. I grew up on Star Wars, play jazz piano, and am an avid gamer.

A Chatbot Framework for Casual Conversation

Virtual conversational agents, or Chatbots, are quickly becoming a ubiquitous element of human-computer interaction, customer-business communications, and entertainment. Natural Language Processing 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. The dialogue that arises from interactions with a user is rooted in the domain of the dialogue system. Is it possible for a Chatbot to handle conversing in the domain of human-like casual conversation?

I am designing a framework for the construction of Chatbot characters capable of human-like casual conversation that integrates rule-based reasoning and human conversational behaviors into the dialogue management 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 have unique personalities. Integrated into this framework is an explicit representation of memory and knowledge, also defined by the Chatbot author, which allows for the Chatbot character to “remember” information from previous interactions with a user. Chatbot characters built around human conversational abilities can provide a more natural means of interaction with a user when equipped with this “memory.” Interactions with these Chatbot characters can 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.

A Chatbot for Casual, Human-Like Conversation

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.

A Chatbot for Casual, Human-Like Conversation

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.

Chatbot Project: 8-Week Syllabus

To understand the work which I am doing this semester, a broader look at the world of the chatbot is needed. With the following readings, students will dive into the potential uses of this virtual conversational agent, and thus my motivations behind pursuing this work. Students will also be introduced the technology and techniques I plan on using. These techniques will be compared with existing techniques which have been used to create virtual conversational agents in the past. Students will interact with multiple existing virtual conversational agents to get a firsthand look at what works and doesn’t work when it comes to interactions with a virtual agent. Students will also get a direct look at the work which I have already completed with regards to this work.

Students will get a look at both the creative and more technical aspects of this project. Students will be assigned tasks which may be more suited for a creative writing class, but also a linguistics class. This project brings multiple areas of study together – thus it is imperative that students understand the relevant areas of each of these fields. Continue reading Chatbot Project: 8-Week Syllabus

A Human-Like Virtual Conversational Agent: Casual Conversation

Virtual conversational agents, by and large, are notoriously ineffective at human-like conversation (albeit fun for humans to interact with). At worst, these agents’ responses come across as gibberish, and at best, they feel unnatural to interact with. Previously, the “best practices” for the construction of these agents has not centered around human-like speech behaviors, but rather around the appearance of human-like behavioral capabilities, the byproduct of machine-learning methods which essentially “train” the agent to mimic patterns which emerge from corpora of conversations.

The work I did at the USC Institute for Creative Technologies (ICT) this past summer in programming a virtual conversational agent centered around human-like conversational behaviors is a jumping off point for creating a virtual agent which portrays human-like conversational abilities for casual conversation. At ICT, we used an alternate method of constructing these virtual agents: we programmed dialogue policies modeled after the conversational behaviors of humans. The virtual agent I would like to create will have: a memory of what it has said and of what the user has said within a conversation; the functionality to recognize what the user has said; a method of using what the user has said in an effective manner; human-like speech utterances and conversational behaviors; and a way to remember this information for use in future conversations. It is my goal this year to create either a method of authoring such an agent, or to construct such an agent myself.