Prototyping a chatbot for practising conversational English with corrective feedback

Abstract

This work focuses on chatbots’ application in the educational domain, and precisely, in the area of foreign language learning. The goal of this project is to create a prototype of a chatbot that aims at improving learners’ English speaking skills by participating in a conversation on a certain topic. The additional feature of this prototype is the chatbot’s ability to generate Corrective Feedback (CF) that allows students to reflect on the mistakes made. The prototype, that was built with the help of the RASA Framework, combines several Natural Language Processing tasks such as automatic Grammar Error Correction and Question Generation. The presented version of the chatbot is capable of identifying errors made by learners and present immediate implicit CF in the form of incorporated interrogative recast