Roni Rabin
Roni Rabin is a research scientist on the Google Research team focusing on Education Innovation using AI. As part of this, Roni is leading the effort of improving large language models' ability to perform crucial educational capabilities such as conducting an evaluative practice multi-turn conversation, generating high quality questions, assessing user answers and more.
Previously, Roni founded and managed a Software Engineering team at Google charged with building tools for journalists. As part of this work, Roni led the launch of Pinpoint - a new research tool for journalists, as well as significant improvements to the Google Trends product which allows analyzing Google Search behavior in aggregate.
Previously, Roni founded and managed a Software Engineering team at Google charged with building tools for journalists. As part of this work, Roni led the launch of Pinpoint - a new research tool for journalists, as well as significant improvements to the Google Trends product which allows analyzing Google Search behavior in aggregate.
Research Areas
Authored Publications
Sort By
Covering Uncommon Ground: Followup Question Generation for Answer Assessment
Alexandre Djerbetian
Reut Tsarfaty
ACL (2023) (to appear)
Preview abstract
In educational dialogue settings students often provide answers that are incomplete. In other words, there is a gap between the answer the student provides and the perfect answer expected by the teacher. Successful dialogue hinges on the teacher asking about this gap in an effective manner, thus creating a rich and interactive educational experience. Here we focus on the problem of generating such gap-focused questions (GFQ) automatically. We define the task, highlight key desired aspects of a good GFQ, and propose a model that satisfies these. Finally, we provide an evaluation of our generated questions and compare them to manually generated ones, demonstrating competitive performance.
View details
