Text Chunking is one of the basic tasks in natural language processing. Most proposed models in recent years were employed on Chunking and other sequence labeling tasks simultaneously and they were mostly based on Recurrent Neural Networks (RNN) and Conditional Random Field (CRF). In this article, we use state-of-the-art transformer-based models in combination with CRF, Long Short-Term Memory (LSTM)-CRF as well as a simple dense layer to study the impact of different pre-trained models on the overall performance in Text Chunking. To this aim, we evaluate BERT, RoBERTa, Funnel Transformer, XLM, XLM-RoBERTa, BART, and GPT2 as candidates of conTextualized models. Our experiments exhibit that all transformer-based models except GPT2 achieved close and high scores on Text Chunking. Due to the unique unidirectional architecture of GPT2, it shows a relatively poor performance on Text Chunking in comparison to other bidirectional transformer-based architectures. Our experiments also revealed that adding a LSTM layer to transformer-based models does not significantly improve the results since LSTM does not add additional features to assist the model to achieve more information from the input compared to the deep conTextualized models.

Text tokenization is the process of tokenizing Text to meaningful tokens such as words, phrases, sentences, etc. Tokenization of syntactical phrases named as Chunking is an important preprocessing needed in many applications such as machine translation information retrieval, Text to speech, etc. In this paper Chunking of Farsi Texts is done using statistical and learning methods and the grammatical characteristics of Farsi Texts. Many features and labeling methods are examined one by one and the best features and labeling techniques are used for the detection of syntactic phrases and their boundaries. Several machine learning techniques including Support Vector Machine and Conditional Random Fields are used as classifier in our experiments. The impact of the size of training Texts on Chunking performance was studied as well. Using the proposed methods in this paper, a performance of 84.02% was obtained for detection of phrase boundaries and 78.04% for detection of both phrase boundaries and phrase type.

In this article, the writers make a distinction between two types of Text, open Text and closed Text. While the latter has a fixed and limited meaning, fixed signifiers and signifieds, with the signs always referring the reader to a fixed world, the former has the potential to be loaded with various meanings. To explicate the two types of Text and the factors that make a Text open, the writers draw on the views of great thinkers such as Rolan Barthes, Wolfgang Izer, Jacques Derrida and Carl Gustav Yung. The purpose of the article is to show how a familiarity with the western interpretations of Hermeneutics can affect our appreciation of Persian literature.

In this paper one of the main forms of Textualization will be represented; little known, in our opinion, first by foreign language specialists (linguists or literary) in Iran and marginalized, even absent, from the educational applications in language and literature courses in the Iranian universities.After an overview of the types of Texts, we will try to develop the idea that concerns us here, namely the study of argumentative type in two ways: firstly the epistemological concept of argumentation and then the organization of the argumentative Text. French: Le Texte argumentatif et la typologie de TextesResume Cet article aura comme but de representer l’une des formes principales de Textualisation, peu connue, a notre avis, d’abord par les specialistes des langues etrangeres (linguiste ou litteraire) en Iran et marginalisee, et meme absente, par consequent, des applications pedagogiques dans les cours de langue et litterature au milieu universitaire iranien.Apres un apercu general de la typologie des Textes, nous avons essaye de mettre au point l’idee qui nous preoccupe ici, a savoir l’etude du type argumentatif sur deux plans: d’abord plan epistemologique de la notion d’argumentation et ensuite plan organisationnel du Texte argumentatif.keywords: Typologie de Textes, Argumentation, Discours Argumentatif, Organisation de Texte, Categories de la Langue

One of the most important information security techniques is the hiding of information. Steganography is the art and science of hiding information in the cover of data (in the form of Text, image, video, or audio) such that it does not arise any suspicions, and is difficult or even impossible to discover. This paper presents a method for steganography in the form of Text which uses the methods of Text justifying in typing editors. The method presented in this paper is able to hide information better than some of previous algorithms in this field. This algorithm is resistant to various forms of attack such as visual, structural and statistical attacks. Another important capability of this method is that it can be used to send printed information.

The progress of communications over internet media such as social media and messengers has led to the production of large amount of Textual data. This kind of information contains a lot of valuable knowledge and can be used to improve the performance of other natural language processing (NLP) tasks. There are several ways to use such information, of which one is Text summarization. Summarizing Textual information can extract the main content of Text within a short time. In this paper, we propose an approach for extractive summarization on Persian Texts by using sentences embedding and a sparse coding framework. Most previous works focuses on Text’s sentences individually which may not consider the hidden structure patterns between them. In this paper, our proposed approach can consider the relations between the Text’s sentences by using three main criteria, namely coverage, diversity and sparsity, when selecting the summary sentences. By considering these criteria, we select sentences that can reconstruct the whole Text with least reconstruction error. The proposed approach is evaluated on Persian dataset Pasokh and achieved 10. 02% and 8. 65% improvement compared to the state-of-the-art methods in rouge-1 and rouge-2 f-scores, respectively. We show that considering semantic relations among the Text’s sentences can lead us to better sentence summarization.

The progress of communications over internet media such as social media and messengers has led to the production of large amount of Textual data. This kind of information contains a lot of valuable knowledge and can be used to improve the performance of other natural language processing (NLP) tasks. There are several ways to use such information, of which one is Text summarization. Summarizing Textual information can extract the main content of Text within a short time. In this paper, we propose an approach for extractive summarization on Persian Texts by using sentences embedding and a sparse coding framework. Most previous works focuses on Text’ s sentences individually which may not consider the hidden structure patterns between them. In this paper, our proposed approach can consider the relations between the Text’ s sentences by using three main criteria, namely coverage, diversity and sparsity, when selecting the summary sentences. By considering these criteria, we select sentences that can reconstruct the whole Text with least reconstruction error. The proposed approach is evaluated on Persian dataset Pasokh and achieved 10. 02% and 8. 65% improvement compared to the state-of-theart methods in rouge-1 and rouge-2 f-scores, respectively. We show that considering semantic relations among the Text’ s sentences can lead us to better sentence summarization.

This paper introduces readability or Text difficulty level and the factors contributing thereto from educational perspective in general and for translator training purposes in particular. Two most-frequently applied readability formulas, Flesch and Fog, are presented including the criticisms leveled by translation researchers and linguists against such quantifications. Subsequently, the question of Text difficulty is discussed from translation studies perspective following which Textuality standards, Text type and Text analysis for translator training purposes is put forth. The paper concludes with the introduction of five translation difficulties and problem areas as features presumably shared universally by all languages including Persian. Presented in the final section of this paper is certain guidelines for Text selection and classification in educational settings and for pedagogical purposes; Texts which are compatible with translational competence level of the translation trainees.