Understanding and Facilitating Collaborations
Strand 1 researchers are working to answer the foundational question: What AI advances are needed to understand and facilitate collaborative learning conversations? This team is striving to build our AI Partners’ rich dialogue capability for discussions with students and teachers, both through language and non-verbal communication. Strand 1 researchers take the data collected from the Institute-wide data collection team and figure out how it can be used to define the capabilities of our AI Partner - creating the eyes and the ears of our AI Partner, as well as what the Partner will do with the information the eyes and ears take in. The themes for Strand 1 are: Speech Processing and Diarization, Content Analysis & Dialogue Management (also known as MMIA: Multimodal interactive agent) and Situated Grounding.
Speech Processing & Diarization
This team is working to enable our AI Partner to better understand students when they talk and identify who is speaking and when by improving Automatic Speech Recognition models for classrooms.
Content Analysis & Dialogue Management
This theme is dedicated to helping our Partner make sense of what it’s hearing and seeing and determining optimal interactions between students and teachers. Their work is helping our AI Partner understand key content words and concepts uttered by students.
Situated Grounding
Students and teachers establish common ground when interacting with one another through both behavioral and verbal cues, as well as prior goals, expectations, and beliefs. This theme is identifying this common ground through discourse and gesture.