In today's information age, efficient document ranking plays a crucial role in information retrieval systems. This article proposes a new approach to document ranking using embedding models, with a focus on the BERT language model to improve ranking results. The proposed approach uses vocabulary embedding methods to represent the semantic representations of user queries and document content. By converting textual data into semantic vectors, the relationships and similarities between queries and documents are evaluated under the proposed ranking relationships with lower cost. The proposed ranking relationships consider various factors to improve accuracy, including vocabulary embedding vectors, keyword location, and the impact of valuable words on ranking based on semantic vectors. Comparative experiments and analyses were conducted to evaluate the effectiveness of the proposed relationships. The empirical results demonstrate the effectiveness of the proposed approach in achieving higher accuracy compared to common ranking methods. These results indicate that the use of embedding models and their combination in proposed ranking relationships significantly improves ranking accuracy up to 0. 87 in the best case. This study helps improve document ranking and demonstrates the potential of the BERT embedding model in improving ranking performance.

Using the context and order of words in sentence can lead to its better understanding and comprehension. Pre-trained language models have recently achieved great success in natural language processing. Among these models, The BERT algorithm has been increasingly popular. This problem has not been investigated in Persian language and considered as a challenge in Persian web domain. In this article, the embedding of Persian words forming a sentence was investigated using the BERT algorithm. In the proposed approach, a model was trained based on the Persian web dataset, and the final model was produced with two stages of fine-tuning the model with different architectures. Finally, the features of the model were extracted and evaluated in document ranking. The results obtained from this model are improved compared to results obtained from other investigated models in terms of accuracy compared to the multilingual BERT model by at least one percent. Also, applying the fine-tuning process with our proposed structure on other existing models has resulted in the improvement of the model and embedding accuracy after each fine-tuning process. This process will improve result in around 5% accuracy of the Persian web ranking.

In this paper, we firstly review some definitions related to fractional calculus and fractional entropy, as a generalization of Shannon entropy. Then we introduce the generalized word importance metric based on fractional entropy. Using the proposed definition, we introduce a new text mining method based on fractional entropy. This method for keyword extraction of the Statistical Inference book by Casella and Berger (1990) shows that the F-measure value of the proposed text mining method, is higher than the related value for common text mining method based on Shannon entropy. These results indicate that the proposed text mining method based on fractional entropy is more comprehensive than the traditional text mining based on Shannon entropy.

The necessity of an exhaustive research about word making in Arabic language is obvious since the studies and reviews show the perpetuation of Arabic contemporary language. Linguistic scholars and theorists have different opinions about word making process in the sense of applying a new equivalence, producing, creating, and forming new words based on Arabic origins. They also point tothe basis of Arabic word making principles for obtaining a new relation and sense in the original language, or translating foreign and nonnative technical terms fromtarget language. So, the aim of the author of this research is to review, study and determine the complete patterns of word making in contemporary Arabic language which include all the applied and favorable methods of Arabic linguistics and ideas of Arabic language theorists. Also, this research will determine language Equalization, division, and branching in a correct way. Along with the mentioned aims, the present study is organized on the basis of considered patterns of word making styles, analyzing and sampling. The final part of this research shows that the most common word making patterns of the contemporary Arabic language include derivation by seven derivative forms: inflectional derivation, great derivation, greater derivation, major derivation, substitutive derivation, repository derivation and syntactic derivation. The second most common style include tree structures: participle structure, propositional structure, and syntactic structure with a proposition letter group.

The interaction between syntax and word-formation has been of great theoretical significance in the past four decades. The question that is now raised is as follows: is word-formation an independent module, or should it be subsumed under syntax?Considering word-formation processes in Persian, this article is an attempt to provide a number of facts in favour of the existence of an independent word-formation component. These facts are:1. A great number of complex words in Persian are headless, contrary to the syntactic phrases.2. A great number of the Persian compounds have meanings which are predictable, yet different from their compositional meanings.3. The syntactic category of a large number of the Persian compounds is different from that of their constituent words.4. The derivational suffix “-i”, while added to nouns, may make adjectives or nouns, according to which we need to devide the Persian nouns into two subgroups. But this distinction is irrelevant in syntax.5. The Persian inflectional morphemes do not occur inside compounds.6. Compounds and syntactic phrases have different stress patterns.