Building Bridges between Student and Curricular Language: Creating a Corpus of Abstract Meaning Representations for the Classroom

Abstract

The potential of AI conversational agents to foster student learning and reduce teacher strain in classroom settings has made the development of pedagogical agents a prime research target. An effective AI agent in particular must be able to understand both student language and the content they are learning and, furthermore, map between them. Curricular terminology and student speech, though topically and semantically related, differ significantly in surface-form expression. We present the JIA-AMRs Collection, a new resource for exploring whether Abstract Meaning Representations (AMRs) can optimize interventions by a conversational AI agent in a middle-school classroom by providing structured semantic representations of classroom language. This resource also provides an avenue by which we can verify interventions by the agent. We discuss the challenges of creating a corpus of meaning representations that map across highly-dissimilar classroom data (multimedia curriculum, student spoken language, and student written language) and our promising results of a nearly 30-point gain in trained-parser performance over the off-the-shelf model.

Resources

Details