Tailored feedback in language learning: synergies in linguistics and computer science

Caregivers provide feedback to children in dialogue via repetition, elaboration, corrective feedback, and modelling adult conversation. While previous research has primarily focused on the use and usefulness of corrective feedback to syntactic constructions (Marcus, 1993; Hiller & Fern ´andez 2016), there is a notable gap in our knowledge about the role of situation-specific modelling
of adult-like behaviour for pragmatic development.

Prior work analysing this behaviour is often based on individual case studies due to the resource intensity of analysing child language data. We exploit the powerful representations within, and classification ability of computational language models (LMs, large pretrained causal transfromer models e.g. the GPT
family) to recognise and analyse different types of feedback.