Abstract:Preprocessing is one of the main components in a conventional document categorization (DC) framework. This paper aims to highlight the effect of preprocessing tasks on the efficiency of the Arabic DC system. In this study, three classification techniques are used, namely, naive Bayes (NB), k-nearest neighbor (KNN), and support vector machine (SVM). Experimental analysis on Arabic datasets reveals that preprocessing techniques have a significant impact on the classification accuracy, especially with complicated morphological structure of the Arabic language. Choosing appropriate combinations of preprocessing tasks provides significant improvement on the accuracy of document categorization depending on the feature size and classification techniques. Findings of this study show that the SVM technique has outperformed the KNN and NB techniques. The SVM technique achieved 96.74% micro-F1 value by using the combination of normalization and stemming as preprocessing tasks.

The fast-growing amount of information on the Internet makes the research in automatic document summarization very urgent. It is an effective solution for information overload. Many approaches have been proposed based on different strategies, such as latent semantic analysis (LSA). However, LSA, when applied to document summarization, has some limitations which diminish its performance. In this work, we try to overcome these limitations by applying statistic and linear algebraic approaches combined with syntactic and semantic processing of text. First, the part of speech tagger is utilized to reduce the dimension of LSA. Then, the weight of the term in four adjacent sentences is added to the weighting schemes while calculating the input matrix to take into account the word order and the syntactic relations. In addition, a new LSA-based sentence selection algorithm is proposed, in which the term description is combined with sentence description for each topic which in turn makes the generated summary more informative and diverse. To ensure the effectiveness of the proposed LSA-based sentence selection algorithm, extensive experiment on Arabic and English are done. Four datasets are used to evaluate the new model, Linguistic Data Consortium (LDC) Arabic Newswire-a corpus, Essex Arabic Summaries Corpus (EASC), DUC2002, and Multilingual MSS 2015 dataset. Experimental results on the four datasets show the effectiveness of the proposed model on Arabic and English datasets. It performs comprehensively better compared to the state-of-the-art methods.

With continuing global growth of Internet networks and the increase of the amount of texts comes the increased need for automatic summarization. Researchers introduced several methods for article summarization and highlighted the most important information pertaining to this subject. They also discussed the linguistic methods that rely on rhetorical and linguistic tools to analyze the text by pinpointing the semantic and rhetorical links between different text units to determine the proportional relationship between each other, while others discuss the statistical methods using a semi-supervised learning technique and statistical theories based on a group of digital measures that was dependent on and was transferred to a degree to highlight the importance of each sentence(s) in the article. In this paper, we propose a simplified explanation for each method, and the results will be used to highlight the advantages and disadvantages for each method. Our results showed that the statistical method is more effective, especially when the text is long, whereas the linguistic method is effective when the text is short. For these reasons, and to take the advantage of both methods, we propose a new method based on the length of the text. Our experimental results proved the efficiency and effectiveness of the means to obtain better results, and this method is powerful and flexible enough to successfully target a range of different domains and summarization tasks. This method is called Hybrid Summarization System (HSS).

Abstract-The paper discusses the methods used to rough set theory knowledge to discovery from decision tables. From this ways dynamic reduct. Discovery relative static and dynamic reducts, discovery frequent sets, discovery decision rules and calculate stability coefficients for objects from a decision table.The most important and matchless feature of dynamic reduct is ability to calculate stability coefficients for every object from decision table using different methods. In this study we present some statistical arguments showing the introduced stability coefficient of dynamic reducts are proper measures of their quality.

No abstract