AI Seminar: ALOHA: Artificial Learning of Human Attributes for Dialogue Agents

Friday, January 24, 2020 1:00 pm - 1:00 pm EST (GMT -05:00)

Steven Y. Feng
David R. Cheriton School of Computer Science

For conversational AI and virtual assistants to communicate with humans in a realistic way, they must exhibit human characteristics such as expression of emotion and personality. Current attempts toward constructing human-like dialogue agents have presented significant difficulties. 

We propose Human Level Attributes (HLAs) based on tropes as the basis of a method for learning dialogue agents that can imitate the personalities of fictional characters. Tropes are characteristics of fictional personalities that are observed recurrently and determined by viewers’ impressions. By combining detailed HLA data with dialogue data for specific characters, we present a dataset, HLA-Chat, that models character profiles and gives dialogue agents the ability to learn characters’ language styles through their HLAs. We then introduce a three-component system, ALOHA (which stands for Artificial Learning of Human Attributes), that combines character space mapping, character community detection, and language style retrieval to build a character (or personality) specific language model. 

Our preliminary experiments demonstrate that two variations of ALOHA, combined with our proposed dataset, can outperform baseline models at identifying the correct dialogue responses of chosen target characters, and are stable regardless of the character’s identity, the genre of the show, and the context of the dialogue.

Bio: Steven Feng is a Bachelor of Mathematics undergraduate student (Statistics major & CS minor) at the University of Waterloo as well as a Bachelor of Business Administration undergraduate student at the Lazaridis School of Business & Economics at Wilfrid Laurier University.

Steven is also an undergraduate research assistant who has worked with Cheriton School of Computer Science Professors Edith Law, Jesse Hoey and Pascal Poupart as well as Professor Olga Vechtomova from the Faculty of Engineering’s Department of Management Sciences. Since 2018, Steven has contributed to a variety of machine learning research projects, among them two complementary ones with Professor Hoey on conversational assistants, the overall goal of which was to design chatbots and virtual assistants that can imitate human personalities.

Recently, Steven was selected for an honorable mention in the Computing Research Association’s 2020 Outstanding Undergraduate Researcher Awards for his research on on conversational assistants.