UROP Project Report 2021: Providing Automatic Feedback on Argumentation Quality to Learners of English

This research was supported, in part, by an award from Cambridge University Press & Assessment, University of Cambridge.

In collaboration with the ALTA Insitute (Computer Laboratory, University of Cambridge), I helped develop a learning tool that aims to help students learn the skill of argumentation by providing high-level, automatic adaptive feedback on the quality of their argumentation in essays. I was the only first-year undergraduate at Cambridge University accepted to participate in the 2021 UROP in the Natural Language and Information Processing Group. The tool consists of a pre-trained Large Language Model that automatically analyses argumentation structure in written English and a front-end user interface. I helped establish a preliminary pilot study, which was later conducted by Wambsganss, Caines & Buttery (2022). You can find their 2022 ACL Conference Paper that expands on the project here: https://aclanthology.org/2022.bea-1.18/.