Abstract With the popularity of Internet, tremendous amount of unstructured information becomes available. Consequently, extracting related information from large corpus becomes popular and has been studied by many researchers. However, synonym and polysemy, miss spelling, and using abbreviation make the task difficult. Resolving those confusions is known as an Entity Resolution problem. In this paper, we are proposing a multi-level weighted... With the popularity of Internet, tremendous amount of unstructured information becomes available. Consequently, extracting related information from large corpus becomes popular and has been studied by many researchers. However, synonym and polysemy, miss spelling, and using abbreviation make the task difficult. Resolving those confusions is known as an Entity Resolution problem. In this paper, we are proposing a multi-level weighted hybrid feature scheme to resolve mixed entities among unstructured documents. Experimental results show that a weighted hybrid feature improves the accuracy and efficiency. Read More Read Less

Abstract Representative Vector is a kind of Vector which includes related words and the degree of their relationships. In this paper the effect of using this kind of Vector on automatic classification of Persian documents is examined. In this method, preprocessed documents, extra words as well as word stems are at first found. Next, through one of the known ways, some... Representative Vector is a kind of Vector which includes related words and the degree of their relationships. In this paper the effect of using this kind of Vector on automatic classification of Persian documents is examined. In this method, preprocessed documents, extra words as well as word stems are at first found. Next, through one of the known ways, some features are extracted for each category. Then, the Representative Vector, which is made based on the elicited features, leads to some more detailed words which are better Representatives for each category. Findings of the experiments show that Precision and Recall can be increased significantly by extra words omission and addition of few words in the Representative Vectors as well as the use of a famous classification model like Support Vector Machine (SVM). Read More Read Less

Abstract Under the term “data mining”, the field of computer science includes many different techniques for data analysis, among them methods of cluster analysis. In the approach presented, a special method is designed for the analysis of inflectional systems. The algorithm is independent of individual natural languages and parts of speech. It finds two types of clusters: morphologically homogeneous ones, which... Under the term “data mining”, the field of computer science includes many different techniques for data analysis, among them methods of cluster analysis. In the approach presented, a special method is designed for the analysis of inflectional systems. The algorithm is independent of individual natural languages and parts of speech. It finds two types of clusters: morphologically homogeneous ones, which contain reversely similar (which possess the same trailing letters), morphologically analogous lexemes of the examined language-part-of-speech combination, and morphologically inhomogeneous ones, in which the largest part of the lexemes is morphologically homogeneous. The resulting registers are compact and transparent as well as easily extensible and correctible. In condensed form, they provide linguistically and didactically usable, structural results on inflectional systems. For instance, it is possible to assign arbitrary lexemes to clusters with a detailed explanation based upon the structure of an inflectional system. The approach is most often applied to verb systems in inflecting and agglutinating language. Read More Read Less

Abstract In the past few years, researchers have started paying attention to the Arabic language. In this paper we review information extraction systems that were developed for the Arabic to extract predefined entities. A comparisons are conducted between these systems in terms of their performance in extracting the common entities, the approach used whether rule-based or machine learning and type of... In the past few years, researchers have started paying attention to the Arabic language. In this paper we review information extraction systems that were developed for the Arabic to extract predefined entities. A comparisons are conducted between these systems in terms of their performance in extracting the common entities, the approach used whether rule-based or machine learning and type of corpus. Read More Read Less