In specialized fields, the accurate answering of visual questions is crucial for practical applications, and this study focuses on improving a visual question-answering model for artistic images by utilizing a dataset with both visual and knowledge-based questions. The approach involves employing a pre-trained BERT model to understand query nature and using the iQAN model with MLB and MUTAN mechanisms for visual queries, along with an XLNet-based model for knowledge-based information. The results demonstrate a 78.92% accuracy for visual questions, 47.71% for knowledge-based questions, and an overall accuracy of 55.88% by combining both branches. Additionally, the research explores the impact of parameters like the number of glances and activation functions on the model's performance.

Contemporary machine learning models, like deep neural networks, require substantial labeled datasets for proper training. However, in areas such as natural language processing, a shortage of labeled data can lead to overfitting. To address this challenge, data augmentation, which involves transforming data points to maintain class labels and provide additional valuable information, has become an effective strategy. In this paper, a deep reinforcement learning-based text augmentation method for sentiment analysis was introduced, combining reinforcement learning with deep learning. The technique uses Deep Q-Network (DQN) as the reinforcement learning method to search for an efficient augmentation strategy, employing four text augmentation transformations: random deletion, synonym replacement, random swapping, and random insertion. Additionally, various deep learning networks, including CNN, Bi-LSTM, Transformer, BERT, and XLNet, were evaluated for the training phase. Experimental findings show that the proposed technique can achieve an accuracy of 65.1% with only 20% of the dataset and 69.3% with 40% of the dataset. Furthermore, with just 10% of the dataset, the method yields an F1-score of 62.1%, rising to 69.1% with 40% of the dataset, outperforming previous approaches. Evaluation on the SemEval dataset demonstrates that reinforcement learning can efficiently augment text datasets for improved sentiment analysis results.