Casey Kennington, Ph.D.

Bio

Casey Kennington, PhD is an associate professor in the Boise State University Computer Science department.

He is a recipient of a National Science Foundation CAREER award that supports researching how language models learn, how they come to represent and process natural human language, how they could be made smaller, and how they could make use of data beyond just text. Other funded research includes dialogue system infrastructure for natural spoken communication with robots. He leads the Speech, Language, & Interactive Machines (SLIM) research group at BSU.

He has led the effort to create the upcoming BS in AI Science degree (in the review process at the State Board of Education).He proposed and taught original coursework for the Machine Learning Emphasis in the CS major, which is very popular.  He also led the efforts to create the Data Science emphasis in the PhD in Computing program. He has also been instrumental in data science and AI efforts across the campus. He teaches courses in Natural Language Processing, Deep Learning, and Data Science. 

After Completing a bachelor’s degree at Brigham Young University in CS, Casey went onto the Erasmus Mundus LCT Master’s Program where he completed a master’s degree in computational linguistics from Saarland University (Germany) and cognitive science from Nancy 2 University (now Lorraine University; France). He completed his PhD at Bielefeld University (Germany).

Areas of Interest

• Language comprehension and understanding such that an abstraction sufficient enough for a later consumer (such as a dialogue manager) is produced. This of necessity includes speech recognition, and may include syntax and semantics where necessary. In this research area, questions like how should meaning be represented? and how are entities related? are explored.
• Language acquisition. A dialogue system should be able to learn new concepts (i.e., words and language constructs) online as it interacts. Some concepts of necessity are grounded in the “real world” (e.g., what is the notion of redness / what does red mean?) where other concepts are more abstract or deal with how dialogue should work (e.g., when should a clarification request be made, and what kind of request?).
• Interaction between humans as well as interaction between humans and machines. It is through this interactive process that common ground is established, which is key to comprehension, and it is through interaction that new concepts are acquired and built upon. The interaction should be tightly-coupled (i.e., incremental) as it is with humans, not only because we want people to interact with and use our systems, but also to understand ourselves.
• Non-verbal behaviour. Language isn’t the only medium of communication. Gestures too can convey a lot of information (e.g., when someone points and says “that” or when someone shapes their hands in a certain way to convey a specific shape). Also, body language, head nods, facial features, and eye gaze can be very communicative. I am mostly interested in how these mediums interact with language.