Assessing Free Student Answers in Tutorial Dialogues Using LSTM Models

Nabin Maharjan, Dipesh Gautam, Vasile Rus

Abstract: In this paper, we present an LSTM approach to assess free short answers in tutorial dialogue contexts. A major advantage of the proposed method is that it does not require any sort of feature engineering. The method performs on par and even slightly better than existing state-of-the-art methods that rely on expert-engineered features.