Document Type

Poster

Publication Date

Fall 2020

Abstract

Improvisational theater is an art form where unscripted theater is performed. Dialogue, characters, and actions are created on the spot. Errors made within an improvisational theater scene are encouraged, and can form an input to how the scene evolves. Ultimately this project focuses on the evolution and creation of artificial intelligence bots interacting with the world of improv theater. Chatbots Versus Improv Bots A chatbot is a software application used to conduct an online chat conversation via text or text-to-speech, in lieu of providing direct contact with a live human agent. There are many different types of chatbots ranging from a regular expression chatbot like Eliza, who was designed to imitate a therapist, a slot-response chatbot such as Amazon’s Alexa, who responds and acts on commands, or even neural nets like GPT-2 , BERT, or XLNet all of which are used for various elements of natural language processing and text classification tasks. The Artificial Improvisor is a form of artificial conversational agent, or chatbot, focused on open domain dialogue and collaborative narrative generation. Using state-of-the-art machine learning techniques, spanning from natural language processing and speech recognition, to reinforcement and deep learning, these improv bots provide a completely new and exciting asset to this technology that is different from these other types of chatbots. Below is an example of each type of chatbot listed in order from left to right.

Creative Commons License

Creative Commons Attribution 4.0 License
This work is licensed under a Creative Commons Attribution 4.0 License.

Share

COinS
 
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.