Mohsen Maraoui

Intertextual distance for Arabic texts classification

Our researches works are interested on the application of the intertextual distance theory on the Arabic language as a tool for the classification of texts. This theory assumes the classification of texts according to criteria of lexical statistics, and it is based on the lexical connection approach. Our objective is to integrate this theory as a tool of classification of texts in Arabic language. It requires the integration of a metrics for the classification of texts using a database of lemmatized and identified corpus which can be considered as a literature reference for times, kinds, literary themes and authors and this in order to permit the classification of anonymous texts.

Latent Topic Model for Indexing Arabic Documents

In this paper, the authors present latent topic model to index and represent the Arabic text documents reflecting more semantics. Text representation in a language with high inflectional morphology such as Arabic is not a trivial task and requires some special treatments. The authors describe our approach for analyzing and preprocessing Arabic text then we describe the stemming process. Finally, the latent model (LDA) is adapted to extract Arabic latent topics, the authors extracted significant topics of all texts, each theme is described by a particular distribution of descriptors then each text is represented on the vectors of these topics. The experiment of classification is conducted on in house corpus; latent topics are learned with LDA for different topic numbers K (25, 50, 75, and 100) then the authors compare this result with classification in the full words space. The results show that performances, in terms of precision, recall and f-measure, of classification in the reduced topics space outperform classification in full words space and when using LSI reduction.

SCAT: A System of Classification for Arabic texts

The core of this work is to realise a system of classification for Arabic texts (SCAT) based on the inter-textual distance theory for Arabic language. This theory assumes the classification of texts according to criteria of lexical statistics, and it is based on the lexical connection approach. Our objective is to integrate this theory as a tool of classification of texts in Arabic language. It requires the integration of a metrics for the classification of texts using a database of lemmatised and identified corpus which can be considered as a literature reference for times, kinds, literary themes and authors and this in order to permit the classification of anonymous texts.

Probabilistic Approach for Detection of Vocal Pathologies in the Arabic Speech

There are different methods for vocal pathology detection. These methods usually have three steps which are feature extraction, feature reduction and speech classification. The first and second steps present obstacles to attain high performance and accuracy of the classification system [20]. Indeed, feature reduction can create a loss of data. In this paper, we present an initial study of Arabic speech classification based on probabilistic approach and distance between reference speeches and speech to classify. The first step in our approach is dedicated to generate a standard distance (phonetic distance) between different healthy speech bases. In the second stage we will determine the distance between speech to classify and reference speeches (phonetic model proper to speaker and a reference phonetic model). Comparing these two distances (distance between speech to classify and reference speeches & standard distance), in the third step, we can classify the input speech to healthy or pathological. The proposed method is able to classify Arabic speeches with an accuracy of 96.25%, and we attain 100% by concatenation falsely classified sequences. Results of our method provide insights that can guide biologists and computer scientists to design high performance systems of vocal pathology detection.

LDA and LSI as a Dimensionality Reduction Method in Arabic Document Classification

In this work, we made an experimental study for compare two approaches of reduction dimensionality and verify their effectiveness in Arabic document classification. Firstly, we apply latent Dirichlet allocation (LDA) and latent semantic indexing (LSI) for modeling our document sets OATC (open Arabic Tunisian corpus) contained 20.000 documents collected from Tunisian newspapers. We generate two matrices LDA (documents/topics) and LSI (documents/topics). Then, we use the SVM algorithm for document classification, which is known as an efficient method for text mining. Classification results are evaluated by precision, recall and F-measure. The evaluation of classification results was performed on OATC corpus (70 % training set and 30 % testing set). Our experiment shows that the results of dimensionality reduction via LDA outperform LSI in Arabic topic classification.

Automating Event Recognition for SMT Systems

Event Named entity Recognition (NER) is different from most past research on NER in Arabic texts. Most of the effort in named entity recognition focused on a specific domains and general classes especially the categories; Organization, Location and Person. In this work, we build a system for Event named entities annotation and recognition. To reach our goal we combined between linguistic resources and tools. Our method is fully automatic and aims to ameliorate the performance of our machine translation system.

Use of NLP Tools in CALL System for Arabic

This article focuses on the development of Natural Language Processing (NLP) tools for Computer Assisted Language Learning (CALL). First, we have developed some NLP tools: a labelled dictionary of Arabic (as complete as possible), a generator for morphological derivatives, a Conjugator and a morphological analyzer for Arabic. Second, we used these tools to create a number of educational applications for learning the Arabic language by using the proposed system SALA (an NLP-based authoring system, organized into three distinct layers: functions, scripts and activities).

The Gemination Effect on Consonant and Vowel Duration in Standard Arabic Speech

In this paper, we expose the results of an experimental study of acoustic properties of geminated consonants in Arabic language. We aim to determinate the temporal relationship between doubled consonant and the length of the vowel preceding them in a VCCV sequence. We compare these values with those measured for a VCV sequence. The results proved that the duration of simple consonant was sensibly different from the geminated one and same for the duration of the vowel preceding it. This work was undertaken to determinate the consonant duration characteristics to distinguish between a simple consonant and the geminated one in standard Arabic speech recognition.

Pedagogical Indexed Arabic Text in Cloud E-Learning System

The Cloud E-Learning Systems for the Arabic language are relevant environments in many areas of training teaching Arabic language but also pose problems related to their creation tedious, costly in resources and time, and problems related to the search for information because of the increasing amount of information available and because of the methods of indexing, which is based on static methods such as keyword search that makes irrelevant the research process. For this, a new method of indexation is required. In this paper, a new Arabic text is proposed indexing approach using the creation of a new application profile of the LOM metadata schema Learning Object Metadata for the Arabic language. This profile includes the fields of LOM standard, and adds new fields for specific search information to Arabic language, and meets the needs of a teacher. Also, its all using natural language processing tools like SAPA and AL-KHALIL.

Hybrid modeling of an OffLine Arabic Handwriting Recognition System AHRS

Handwriting Recognition HR is the old dream of all those who need to enter data into a computer. In this article, we present a state of the art in the field of handwriting recognition by focusing primarily on Arabic handwritten script which we present an overview of the Offline Automatic Arabic Handwriting Recognition Systems AHRS and the techniques and strategies used. Then, to try to resolve the problems inherent in Arabic handwriting, within the general framework of Arabic Handwriting Recognition and to meet the need to test a new method of learning, we model a new Offline Arabic Handwriting Recognition System AHRS which we detail the architecture of our system and the contributions offered at each stage: preprocessing, segmentation, features extraction, classification and post-processing.