Abdelmajid Ben Hamadou

• PhD & Thèse d'Etat
• Research Director at University of Sfax

The emergence of the Internet and social media has provided a ground conducive to the rapid development of violent ideas and online malicious behavior, and even to rising the share of hostile content (hate speech, fake news, etc.). Such behavior raises concerns about children who are overly exposed to the internet and likely misusing the online con...

With the spreading use of online social networks (OSNs) such as Facebook, Twitter and Youtube, most people find that writing about their feelings and sharing their preferences and thoughts in social media is actually easier then articulating them in real life. Specifically, these networks are increasingly associated with different social phenomena...

The LMF ISO standard provides a large cover of lexical knowledge using a fine structure. However, like most of the electronic dictionaries, the available normalized LMF dictionaries comprise only basic morpho‐syntactic and semantic knowledge, such as the meanings of lexical entries through the definitions and the associated examples, and sometimes...

Recommendation systems have gained the intention of many researchers due to the growth of the business of personalizing, sorting and suggesting products to customers. Most of the rating prediction in recommendation systems are based on customer preferences or on the historical behavior of similar customers. The similarity between customers is gener...

The issue of plagiarism in documents has been present for centuries. Yet, the widespread dissemination of information technology, including the internet, made plagiarism much easier. Consequently, methods and systems aiding in the detection of plagiarism have attracted much research within the last two decades. This paper introduces a plagiarism de...

In the recent years, radical communities have become very aware of the enormous impact of social networks around the world. Thus, these latter are being frequently explored by these groups. Therefore, penetrating into these communities by analyzing both their interactions and their shared content is a considerably challenging task that serves to co...

Social networks are the most successful Web 2.0 applications, where users share and create over 2.5 quintillion bytes of data daily. This data can be exploited to retrieve many kinds of information which will be used in several applications. In fact, social networks have attracted considerable attention from researchers in different domains. This p...

Matching user profiles is an efficient way to map users across social networks and communicate an accurate portrait of a user. This study can be applied in different application domains such as recommendation, privacy, cyber-security, etc. In this paper, we address the problem of matching profiles in two popular social networks: YouTube and Twitter...

Nowadays, social networks have become powerful mediums of communication providing information, learning and entertainment. Unfortunately, these platforms can be sorely manipulated by vicious users sharing malicious contents. Therefore, the process of mining and analyzing such published suspicious content is a considerably challenging task that serv...

Learning meaningful representations for different granularities of texts is a challenging and on-going area of research in natural language processing. Recently, neural sentence modeling that learns continuous valued vector representations for sentences in a low dimensional latent semantic space has gained increasing attention. In this work, we pro...

The spread of real-time applications has led to a huge amount of data shared between users. This vast volume of data rapidly evolving over time is referred to as data stream. Clustering and processing such data poses many challenges to the data mining community. Indeed, traditional data mining techniques become unfeasible to mine such a continuous...

Social networks are considered today as revolutionary tools of communication that have a tremendous impact on our lives. However, these tools can be manipulated by vicious users namely terrorists. The process of collecting and analyzing such profiles is a considerably challenging task which has not yet been well established. For this purpose, we pr...

Sentiment analysis, a hot research topic, presents new challenges for understanding users’ opinions and judgments expressed online. They aim to classify the subjective texts by assigning them a polarity label. In this paper, we introduce a novel machine learning framework using auto-encoders network to predict the sentiment polarity label at the wo...

Plagiarism detection it is a challenging task, particularly in natural language texts. Some plagiarism detection tools have been developed for diverse natural languages, especially English. In this paper, we propose, a new plagiarism detection system devoted to Arabic text documents. This system is based on an algorithm that uses a semantic sentenc...

Semantic similarity and relatedness measures have increasingly become core elements in the recent research within the semantic technology community. Nowadays, the search for efficient meaning-centered applications that exploit computational semantics has become a necessity. Researchers, have therefore, become increasingly interested in the developm...

During the past years, ontologies are widely used for representing knowledge of complex domains. Despite that the ontologies (classical ontologies) have become standard for representing knowledge; however, they are not able to represent and reason with uncertainty which is one of the characteristics of the world that must be handled. Probabilistic...

Sentence similarity computing is increasingly growing in several applications, such as question answering, machine-translation, information retrieval and automatic abstracting systems. This paper firstly sums up several methods to calculate similarity between sentences which consider semantic and syntactic knowledge. Second, it presents a new metho...

Social networks are considered today as revolutionary tools of communication that have a tremendous impact on our lives. However, these tools can be manipulated by vicious users namely terrorists. The process of collecting and analyzing such profiles is a considerably challenging task which has not yet been well established. For this purpose, we pr...

Social media are invaded our daily life where millions of users are subscribed. Those online sites provide great tool for users to communicate with others from all over the world, share information, and express their opinion. Unfortunately, this ease of access and availability of information is exploited by malicious users to spread their radical i...

Since the age of paper versions, dictionaries are often published with anomalies in their content resulting from lexicographer’s mistakes or from the lack of efficiency of automatic enrichment systems. Many of these anomalies are expensive to manually detect and difficult to automatically control, notably with lightly structured models of dictionar...

During the past years, ontologies are widely used for representing knowledge of complex domains. Despite that the ontologies (classical ontologies) have become standard for representing knowledge; however, they are not able to represent and reason with uncertainty which is one of the characteristics of the world that must be handled. Probabilistic...

In (Hlel et al. 2016), we have presented an extension of OWL2 meta-model, called Probabilistic Ontology Definition Meta-model (PODM), for representing the fundamental elements of probabilistic ontologies (POs). Indeed, we have presented a list of new probabilistic components which allow representing the probabilistic basic elements of a domain of i...

Since the age of paper versions, dictionaries are often published with anomalies in their content resulting from lexicographer’s mistakes or from the lack of efficiency of automatic enrichment systems. Many of these anomalies are expensive to manually detect and difficult to automatically control, notably with lightly structured models of dictionar...

Almost all languages lack sufficient resources and tools for developing Human Language Technologies (HLT). These technologies are mostly developed for languages for which large resources and tools are available. In this paper, we deal with the underresourced languages, which can benefit from the available resources and tools to develop their own HL...

La date de publication ne nous a pas encore été communiquée

This paper introduces a new approach for hand gesture recognition based on depth Map captured by an RGB-D Kinect camera. Although this camera provides two types of information "Depth Map" and "RGB Image", only the depth data information is used to analyze and recognize the hand gestures. Given the complexity of this task, a new method based on edge...

In this paper, we address the problem of the large coverage dictionaries of Arabic language usable both for direct human reading and automatic Natural Language Processing. For these purposes, we propose a normalized and implemented modeling, based on Lexical Markup Framework (LMF-ISO 24613) and Data Registry Category (DCR-ISO 12620), which allows a...

In this paper, we have proposed a novel mechanism to discover interests of authors taking into account the meaning of their publications words. For this aim, we have used Bayesian network and WordNet. WordNet is used for determining for each publication the different synsets of its words and its hypernyms (this list of concepts is considered as the...

In this paper, we propose an approach for the self-enrichment of LMF normalized dictionaries with semantic classes. This approach is composed of four processes. The first one deals with the semantic classification process based on the proposition of Gaston Gross. The second benefits from the available subject fields linked to the meanings of the di...

The measure of sentence similarity is useful in various research fields, such as artificial intelligence, knowledge management, and information retrieval. Several methods have been proposed to measure the sentence similarity based on syntactic and/or semantic knowledge. Most proposals are evaluated on English sentences where the accuracy can decrea...

Computing the semantic similarity/relatedness between terms is an important research area for several disciplines, including artificial intelligence, cognitive science, linguistics, psychology, biomedicine and information retrieval. These measures exploit knowledge bases to express the semantics of concepts. Some approaches, such as the information...

The measurement of the semantic relatedness between words has gained increasing interest in several research fields, including cognitive science, artificial intelligence, biology, and linguistics. The development of efficient measures is based on knowledge resources, such as Wikipedia, a huge and living encyclopedia supplied by net surfers. In this...

In this paper, we deal with the representation of syntactic knowledge, particularly the syntactic behavior of verbs. In this context, we propose an approach to identify syntactic behaviors from a corpus based on the LMF Context-Field in order to enrich the syntactic extension of LMF normalized dictionary. Our approach consists of the following step...

Regarding the huge amount of products, sites, information, etc., finding the appropriate need of a user is a very important task. Recommendation Systems (RS) guide users in a personalized way to objects of interest within a large space of possible options. This paper presents an algorithm for recommending movies. We break the recommendation task in...

During the first events of the Tunisian revolution, the social network, Facebook, played a key role in Tunisia and everywhere in the world. It became the first political tool that allows the Tunisian people to share trending news in actual time. Facebook provides the opportunity for users to comment on the news by expressing their sentiments. In th...

This paper presents a novel algorithm to measure semantic similarity between sentences. It will introduce a method that takes into account of not only semantic knowledge but also syntactico-semantic knowledge notably semantic predicate, semantic class and thematic role. Firstly, semantic similarity between sentences is derived from words synonymy....

Declarative approaches to solving the problem of Pattern Mining in Sequences (EMS) constitute an interesting technique transforming the EMS problem into another equivalent NP-Complete problem and trying to solve it by using specialized solvers. In this paper, we will present two existing declarative approaches the first transforms EMS problems int...

This paper proposes a general framework for automatic core domain ontology generation from LMF (ISO 24613) standardized dictionaries. The originality of this work lies not only in the use of a unique and finely structured source containing multi-domain and lexical knowledge of morphological, syntactic and semantic levels, lending itself to ontologi...

The pattern mining in sequences is an important research field, especially in computational biology and text mining. Many approaches are proposed to resolve this problem. The declarative approach is one of them and consists to transform the pattern mining problem into another NP-Complete problem like SAT and CSP. In this paper, we try to compare se...

In this article, we have proposed an extension of OWL2 meta-model for representing the fundamental elements of probabilistic ontologies (POs). This meta-model, called Probabilistic Ontology Definition Meta-model (PODM), provides support for defining probabilistic ontologies. In addition, we have enriched PODM (by using Object Constraint Language) w...

The pattern mining in sequences is an important research field, especially in computational biology and text mining. Many approaches are proposed to resolve this problem. The declarative approach is one of them and consists to transform the pattern mining problem into another NP-Complete problem like SAT and CSP. In this paper, we try to compare se...

The main challenge of this paper is the syntactico-semantic enrichment of LMF normalized dictionaries. To meet this challenge, we propose an approach based on the content of these dictionaries, namely the “Context” fields and the syntactic and semantic knowledge. The proposed approach is composed of three phases. The first one deals with the data s...

The Bayesian network, a probabilistic model of knowledge representation, has the ability to represent and reason with uncertainty. It measures the dependencies between a set of variables and infer new knowledge. In this paper, we try to propose a method for building a probabilistic ontology, which models a list of publications (dblp base). We have...

This paper reports on the status of an ongoing work to enrich the syn-tactic extension of normalized LMF dictionaries. It proposes an approach to find out the syntactic behaviors associated with the lexical entries and to link them to the corresponding meanings of these entries. The used corpus is con-structed from texts associated with each meanin...

In this paper we propose an approach for identifying syntactic behaviours related to lexical items and linking them to the meanings. This approach is based on the analysis of the textual content presented in LMF normalized dictionaries by means of Definition and Context classes. The main particularity of these contents is their large availability a...

Clustering words is a widely used technique in statistical natural language processing. It requires syntactic, semantic, and contextual features. Especially, semantic clustering is gaining a lot of interest. It consists in grouping a set of words expressing the same idea or sharing the same semantic properties. In this paper, we present a new metho...

Many methods for measuring the semantic similarity between sentences have been proposed, particularly for English. These methods are considered restrictive as they usually do not take into account some semantic and syntactic-semantic knowledge like semantic predicate, thematic role and semantic class. Measuring the semantic similarity between sente...

Grouping like-minded users is one of the emerging problems in Social Network Analysis. Indeed, it gives a good idea about group formation and social network evolution. Also, it explains various social phenomena and leads to many applications, such as friends suggestion and collaborative filtering. In this paper, we introduce a novel unsupervised me...

This paper presents a new active learning to rank algorithm based on boosting for active ranking functions. The main goal of this algorithm is to introduce unlabeled data in the learning process. Since this type of ranking is based on a phase of selection of the most informative examples to label, the proposed algorithm allows the cost of labeling...

Data mining is a set of methods used in the process of KDD(Knowledge Discovery in Data) in order to distinguish relationships and unknown patterns in the data. Mining patterns is an interesting technique and is widely used in data mining; its objective is to find the patterns that appear frequently in a database. The sequence mining is the pattern...

In this paper, we propose a CSP-based encoding for the problem of discovering frequents and closed patterns in a sequence. We show that is possible to employee constraint programming techniques for modeling and solving a wide variety of constraint-based item-set mining tasks, such as frequent, closed and maximal. Preliminary experiments show that t...

Proc. of Logistique et transport (LT2007), pp. 347-352, 2007.

Many methods for measuring the semantic similarity between sentences have been proposed, particularly for English. These methods are considered restrictive as they usually do not take into account some semantic and syntactic-semantic knowledge like semantic predicate, thematic role and semantic class. Measuring the semantic similarity between sente...

Several challenges accompanied the growth of online social networks, such as grouping people with similar interest. Grouping like-minded people is of a high importance. Indeed, it leads to many applications like link prediction and friend or product suggestion, and explains various social phenomenon. In this paper, we present two methods of groupin...

In this paper, we present our submitted MT system for the IWSLT2014 Evaluation Campaign. We participated in the English-French translation task. In this article we focus on one of the most important component of SMT: the language model. The idea is to use a phrase-based language model. For that, sequences from the source and the target language mod...

Dictionaries are fundamental linguistic resources for both human and NLP users. Nonetheless, some dictionaries are published with errors and inconsistencies that are difficult and expensive to detect. Only a few works have been devoted to the issue of the automatic detection of anomalies in the dictionaries’ contents. They addressed this issue in a...

Sequence mining is the problem of discovering frequent patterns in sequences. Recently, a declarative approach is proposed to deal with this problem that consists to translate such problem into the enumeration of SAT models. In this paper, we propose to formulate such SAT encoding into a Constraints Programming Problem. Preliminary experiments show...

The challenge of measuring semantic similarity between words is to find a method that can simulate the thinking process of human. The use of computers to quantify and compare semantic similarities has become an important area of research in various fields, including artificial intelligence, knowledge management, information retrieval and natural la...

Relation extraction is a very useful task for several natural language processing applications, such as automatic summarization and question answering. In this paper, we present our hybrid approach to extracting relations between Arabic named entities. Given that Arabic is a rich morphological language, we build a linguistic and learning model to p...

The issue of sentence semantic similarity is important and essential to many applications of Natural Language Processing. This issue was treated in some frameworks dealing with the similarity between short texts especially with the similarity between sentence pairs. However, the semantic component was paradoxically weak in the proposed methods. In...

The issue of sentence semantic similarity is important and essential to many applications of Natural Language Processing. This issue was treated in some frameworks dealing with the similarity between short texts especially with the similarity between sentence pairs. However, the semantic component was paradoxically weak in the proposed methods. In...

In this paper we propose an approach for the automatic enrichment of standardized electronic dictionaries by the semantic classes. This approach consists of three phases. The first phase treat the semantic classification process founded on the studies of Gaston Gross. The second phase profites from the existed subject fields in the dictionary's lex...

With the growth of social media usage, the study of online communities and groups has become an appealing research domain. In this context, grouping like-minded users is one of the emerging problems. Indeed, it gives a good idea about group formation and evolution, explains various social phenomena and leads to many applications, such as link predi...

In this paper, we describe the first tool that detects the semantic relation between Arabic named entities, henceforth RelANE. We use various supervised learning techniques to predict the word or the sequence of terms that can highlight one or more semantic relationship between two Arabic named entities. For each word in the sentence, we use its mo...

Dans l’émergence des méthodes biométriques non-intrusives, l’identification des personnes par la démarche est une piste prometteuse. La plupart des approches existantes analysent la démarche en vue latérale, très peu proposent une reconnaissance sur vue frontale. Ceci s’explique par le fait que les mouvements sont plus difficilement perceptibles da...

Session 5 : Posters et démonstrations

Relation extraction is a very useful task for several natural language processing applications, such as automatic summarization and question answering. In this paper, we present our hybrid approach to extracting relations between Arabic named entities. Given that Arabic is a rich morphological language, we build a linguistic and learning model to p...

In this paper, we deal with the representation of syntactic knowledge, particularly syntactic behavior of Arabic verbs. In this context, we propose an approach to identify the syntactic behavior from corpora in order to enrich the syntactic extension of LMF normalized Arabic dictionary. Our approach is composed of the following steps: (i) Identific...

Dictionaries are used for learning and disseminating natural languages. This important role implies that it is necessary to perform the operations of creating, updating and enrichment carefully. Even in electronic versions, dictionaries may contain anomalies notably when the used acquisition system is not efficient. Several researches have been mad...

Measuring semantic relatedness is a critical task in many domains such as psychology, biology, linguistics, cognitive science and artificial intelligence. In this paper, we propose a novel system for computing semantic relatedness between words. Recent approaches have exploited Wikipedia as a huge semantic resource that showed good performances. Th...

Dictionaries are reference resources for learning and diffusing natural languages. Their contents must be enriched carefully due to their impor-tance. However, such contents might contain er-rors and inconsistencies that are hard to detect manually. Several researches have been made in recent years in order to perform this step auto-matically. Howe...