In the process of verifying Al-Quran memorization, a person is usually asked to recite a verse without looking at the text. This process is generally done together with a partner to verify the reading. This paper proposes a model using Siamese LSTM Network to help users check their Al-Quran memorization alone. Siamese LSTM network will verify the recitation by matching the input with existing data for a read verse. This study evaluates two Siamese LSTM architectures, the Manhattan LSTM and the Siamese-Classifier. The Manhattan LSTM outputs a single numerical value that represents the similarity, while the Siamese-Classifier uses a binary classification approach. In this study, we compare Mel-Frequency Cepstral Coefficient (MFCC), Mel-Frequency Spectral Coefficient (MFSC), and delta features against model performance. We use the public dataset from Every Ayah website and provide the usage information for future comparison. Our best model, using MFCC with delta and Manhattan LSTM, produces an F1-score of 77.35%

Tree-LSTM algorithm accommodates tree structure processing to extract information outside the linear sequence pattern. The use of Tree-LSTM in text generation problems requires the help of an external parser at each generation iteration. Developing a good parser demands the representation of complex features and relies heavily on the grammar of the corpus. The limited corpus results in an insufficient number of vocabs for a grammar-based parser, making it less natural to link the text generation process. This research aims to solve the problem of limited corpus by proposing the use of a Reinforcement Learning algorithm in the formation of constituency trees, which link the sentence generation process given a seed phrase as the input in the Tree-LSTM model. The tree production process is modeled as a Markov’s decision process, where a set of states consists of word embedding vectors, and a set of actions of {Shift, Reduce}. The Deep Q-Network model as an approximator of the Q-Learning algorithm is trained to obtain optimal weights in representing the Q-value function. The test results on perplexity-based evaluation show that the proposed Tree-LSTM and Q-Learning combination model achieves values 9.60 and 4.60 for two kinds of corpus with 205 and 1,000 sentences, respectively, better than the Shift-All model. Human evaluation of Friedman test and posthoc analysis showed that all five respondents tended to give the same assessment for the combination model of Tree-LSTM and Q-Learning, which on average outperforms two other nongrammar models, i.e., Shift-All and Reduce-All.

Automatic short answer scoring is one of the text classification problems to assess students’ answers during exams automatically. Several challenges can arise in making an automatic short answer scoring system, one of which is the quantity and quality of the data. The data labeling process is not easy because it requires a human annotator who is an expert in their field. Further, the data imbalance process is also a challenge because the number of labels for correct answers is always much less than the wrong answers. In this paper, we propose the use of a stacking model based on neural network and XGBoost for classification process with sentence embedding feature. We also propose to use data upsampling method to handle imbalance classes and hyperparameters optimization algorithm to find a robust model automatically. We use Ukara 1.0 Challenge dataset and our best model obtained an F1-score of 0.821 exceeding the previous work at the same dataset.