Although the manual evaluation of essays is a time-consuming process, writing essays has a significant role in assessing learning outcomes. Therefore, automated essay evaluation represents a solution, especially for schools, universities, and testing companies. Moreover, the existence of such systems overcomes some factors that influence manual evaluation such as the evaluator’s mental state, the disparity between evaluators, and others. In this paper, we propose an Arabic essay evaluation system based on a support vector regression (SVR) model along with a wide range of features including morphological, syntactic, semantic, and discourse features. The system evaluates essays according to five criteria: spelling, essay structure, coherence level, style, and punctuation marks, without the need for domain-representative essays (a model essay). A specific model is developed for each criterion; thus, the overall evaluation of the essay is a combination of the previous criteria results. We develop our dataset based on essays written by university students and journalists whose native language is Arabic. The dataset is then evaluated by experts. The experimental results show that 96% of our dataset is correctly evaluated in the overall score and the correlation between the system and the experts’ evaluation is 0.87. Additionally, the system shows variant results in evaluating criteria separately.
We present the first effort towards producing an Arabic Discourse Treebank,a news corpus where all discourse connectives are identified and annotated with the discourse relations they convey as well as with the two arguments they relate.We discuss our collection of Arabic discourse connectives as well as principles for identifying and annotating them in context, taking into account properties specific to Arabic. In particular, we deal with the fact that Arabic has a rich morphology: we therefore include clitics as connectives as well as a wide range of nominalizations as potential arguments. We present a dedicated discourse annotation tool for Arabic and a large-scale annotation study. We show that both the human identification of discourse connectives and the determination of the discourse relations they convey is reliable. Our current annotated corpus encompasses a final 5651 annotated discourse connectives in 537 news texts. In future, we will release the annotated corpus to other researchers and use it for training and testing automated methods for discourse connective and relation recognition.