Publications (6)
Towards Zero-Shot Frame Semantic Parsing with Task Agnostic Ontologies and Simple Labels
Danilo Ribeiro, Omid Abdar, Jack Goetz +4
Frame semantic parsing is an important component of task-oriented dialogue systems. Current models rely on a significant amount training data to successfully identify the intent an…
Data-Efficiency with a Single GPU: An Exploration of Transfer Methods for Small Language Models
Alon Albalak, Akshat Shrivastava, Chinnadhurai Sankar +2
Multi-task learning (MTL), instruction tuning, and prompting have recently been shown to improve the generalizability of large language models to new tasks. However, the benefits o…
Becoming Agents of Change through Participation in a Teacher-Driven Professional Research Community
Mike Ross, Ben Van Dusen, Valerie Otero
This study involves a theory-based teacher professional development model that was created to address two problems. First, dominant modes of science teacher professional developmen…
Teacher-Driven Professional Development and the Pursuit of a Sophisticated Understanding of Inquiry
Mike Ross, Ben Van Dusen, Samson Sherman +1
The need for highly qualified physics teachers in the U.S. is well established, and reform efforts are underway to develop novel and innovative teacher professional development exp…
Large Language Models as Zero-shot Dialogue State Tracker through Function Calling
Zekun Li, Zhiyu Zoey Chen, Mike Ross +7
Large language models (LLMs) are increasingly prevalent in conversational systems due to their advanced understanding and generative capabilities in general contexts. However, thei…
Changing Identities and Evolving Conceptions of Inquiry through Teacher-Driven Professional Development
Ben Van Dusen, Mike Ross, Valerie Otero
This STEM education study investigates the Streamline to Mastery professional development program, in which teachers work in partnership with university researchers to design profe…