ImprovChat: An AI-enabled Dialogue Assistant Chatbot for English Language Learners (ELL)
Yawen’s thesis asks, how can an AI-enabled Dialogue Assistant in the form of a chatbot suggest new and unexpected forms of response to English Language Learners? The thesis draws upon theories of improvisation and play, alongside computer science and programming, to facilitate text-based conversation in English for non-native speakers. ImprovChat is a digital solution for communication issues that Yawen encounters every day. Yawen’s research focuses on developing ImprovChat by implementing an API on top of the customized software powered by machine learning to generate AI phrases from a word-embedding model. This model is pre-trained using literature, as well as the Twitter feeds created by people who speak English as a first language. ImprovChat could be used in online chatting scenarios where participants have two different native languages, or it can be used to inspire unexpected and playful forms of response.
Ginger (Yawen) studied drawing and painting before exploring digital solutions for art in OCAD University. Her studies in the Digital Futures program revealed to her new methodologies for creation. She is very interested in the Chinese and English languages, and tries to include her exploration of the pleasure of text in her artwork.