Off-Topic Essay Detection Using C-BGRU Siamese

Automatic essay evaluation (AEE) and also called automatic essay scoring have become necessary with the rise of online learning and evaluation platforms and several works have been carried out on automatic essay evaluation. Since inputs to such systems come from learners, the system needs a mechanism to validate inputs before evaluation. In this paper, we have proposed a way to validate user responses using an off-topic essay detection method that is used in automatic essay evaluation. In the proposed C-BGRU Siamese architecture, the convolution layer learns and captures the contextual features of the word n-gram from the embedding vectors of the word, and a variant of the RNN so-called bidirectional-gated recurrent unit (BGRU) is used to access both previous and subsequent contextual representations. The experiment was conducted on eight datasets that were based on Kaggle for the task of AEE experimental results show that our proposed method achieves significantly higher accuracy compared to the baseline methods.