Fabrice Evrard

Towards an intelligent possibilistic web information retrieval using multiagent system

Purpose – The purpose of this paper is to make a scientific contribution to web information retrieval (IR).Design/methodology/approach – A multiagent system for web IR is proposed based on new technologies: Hierarchical Small‐Worlds (HSW) and Possibilistic Networks (PN). This system is based on a possibilistic qualitative approach which extends the quantitative one.Findings – The paper finds that the relevance of the order of documents changes while passing from a profile to another. Even if the selected terms tend to select the relevant document, these terms are not the most frequent of the document. This criterion shows the asset of the qualitative approach of the SARIPOD system in the selection of relevant documents. The insertion of the factors of preference between query terms in the calculations of the possibility and the necessity consists in increasing the scores of possibilistic relevance of the documents containing these terms with an aim of penalizing the scores of relevance of the documents no...

ArabOnto: experimenting a new distributional approach for building Arabic ontological resources

Ontologies are useful for modelling and retrieving knowledge in complex information systems. Ontology construction environments use statistical and linguistic information to extract knowledge from corpora. Within the great improvement in this field, there is a need to introduce the Arabic language in these environments. We present the ArabOnto architecture modelling the process of Arabic ontology extraction from corpora. ArabOnto focuses on linguistic issues related to Arabic term extraction and linking (i.e. from morphosyntactic parsing to clustering). We experiment our system by testing several alternatives on three domains. Besides, our ontologies are validated in the context of an information retrieval system.

A Possibilistic Approach for the Automatic Morphological Disambiguation of Arabic Texts

This paper presents a new approach for Arabic non-vocalized texts disambiguation based on a possibilistic classifier. A morphological analyzer provides all the possible solutions and the values of the morphological features of words. When texts are vocalized, the number of solutions is reduced and in many cases, we can identify the correct analysis of the input word. The main idea of this paper is to exploit this type of texts in order to learn contextual dependencies between the different values of morphological features modeled as a possibilistic network. This knowledge is used later to disambiguate non-vocalized texts. In order to evaluate our approach, we perform experiments on a corpus of arabic stories. In this paper, we present results concerning the Part-Of-Speech (POS) which is the main morphological feature. Our results are compared to the SVM-based system called MADA.

Arabic morphological analysis and disambiguation using a possibilistic classifier

This paper proposes and experiments a new approach for morphological feature disambiguation of non-vocalized Arabic texts using a possibilistic classifier. The main idea is to learn contextual dependencies between features from vocalized texts and exploit this knowledge to disambiguate non-vocalized ones. We use possibility theory as a means to model imprecision in the training and testing steps, since the context is itself ambiguous. We also investigate the dependency between various features focusing on the Part-Of-Speech (POS).

Experimenting a discriminative possibilistic classifier with reweighting model for Arabic morphological disambiguation

We perform Arabic morphological disambiguation on unlabeled vocalized corpora.We experiment possibilistic measures for imprecise morphological data classification.We assess the impact of a reweighting model and a possibilistic lexical likelihood.Possibilistic classification is accurate in modern and classical texts disambiguation. In this paper, we experiment a discriminative possibilistic classifier with a reweighting model for morphological disambiguation of Arabic texts. The main idea is to provide a possibilistic classifier that acquires automatically disambiguation knowledge from vocalized corpora and tests on non-vocalized texts. Initially, we determine all the possible analyses of vocalized words using a morphological analyzer. The values of their morphological features are exploited to train the classifier. The testing phase consists in identifying the accurate class value (i.e., a morphological feature) using the features of the preceding and the following words. The appropriate class is the one having the greatest value of a possibilistic measure computed over the training set. To discriminate the effect of each feature, we add the weights of the training attributes to this measure. To assess this approach, we carry out experiments on a corpus of Arabic stories and on the Arabic Treebank. We present results concerning all the morphological features and we discern to which degree the discriminative approach improves disambiguation rates and extract the dependency relationships among the features. The results reveal the contribution of possibility theory for resolving ambiguities in real applications. We also compare the success rates in modern versus classical Arabic texts. Finally, we try to evaluate the impact of the lexical likelihood in morphological disambiguation.

Improving Arabic Texts Morphological Disambiguation Using a Possibilistic Classifier

Morphological ambiguity is an important problem that has been studied through different approaches. We investigate, in this paper, some classification methods to disambiguate Arabic morphological features of non-vocalized texts. A possibilistic approach is improved and proposed to handle imperfect training and test datasets. We introduce a data transformation method to convert the imperfect dataset to a perfect one. We compare the disambiguation results of classification approaches to results given by the possibilistic classifier dealing with imperfection context.

A comparative study between possibilistic and probabilistic approaches for monolingual word sense disambiguation

This paper proposes and assesses a new possibilistic approach for automatic monolingual word sense disambiguation (WSD). In fact, in spite of their advantages, the traditional dictionaries suffer from the lack of accurate information useful for WSD. Moreover, there exists a lack of high-coverage semantically labeled corpora on which methods of learning could be trained. For these multiple reasons, it became important to use a semantic dictionary of contexts (SDC) ensuring the machine learning in a semantic platform of WSD. Our approach combines traditional dictionaries and labeled corpora to build a SDC and identify the sense of a word by using a possibilistic matching model. Besides, we present and evaluate a second new probabilistic approach for automatic monolingual WSD. This approach uses and extends an existing probabilistic semantic distance to compute similarities between words by exploiting a semantic graph of a traditional dictionary and the SDC. To assess and compare these two approaches, we performed experiments on the standard ROMANSEVAL test collection and we compared our results to some existing French monolingual WSD systems. Experiments showed an encouraging improvement in terms of disambiguation rates of French words. These results reveal the contribution of possibility theory as a mean to treat imprecision in information systems.

Towards a New Standard Arabic Test Collection for Mono- and Cross-Language Information Retrieval

We propose in this paper a new standard Arabic test collection for mono- and cross-language Information Retrieval (CLIR). To do this, we exploit the “Hadith” texts and we provide a portal for sampling and evaluation of Hadiths’ results listed in both Arabic and English versions. The new called “Kunuz” standard Arabic test collection will promote and restart the development of Arabic mono retrieval and CLIR systems blocked since the earlier TREC-2001 and TREC-2002 editions.

Improving Query Expansion by Automatic Query Disambiguation in Intelligent Information Retrieval

We study in this paper the impact of Word Sense Disambiguation (WSD) on Query Expansion (QE) for monolingual intelligent information retrieval. The proposed approaches for WSD and QE are based on corpus analysis using co-occurrence graphs modelled by possibilistic networks. Indeed, our model for relevance judgment uses possibility theory to take advantages of a double measure (possibility and necessity). Our experiments are performed using the standard ROMANSEVAL test collection for the WSD task and the CLEF-2003 benchmark for the QE process in French monolingual Information Retrieval (IR) evaluation. The results show the positive impact of WSD on QE based on the recall/precision standard metrics.

A possibilistic query translation approach for cross-language information retrieval

In this paper, we explore several statistical methods to find solutions to the problem of query translation ambiguity. Indeed, we propose and compare a new possibilistic approach for query translation derived from a probabilistic one, by applying a classical probability-possibility transformation of probability distributions, which introduces a certain tolerance in the selection of word translations. Finally, the best words are selected based on a similarity measure. The experiments are performed on CLEF-2003 French-English CLIR collection, which allowed us to test the effectiveness of the possibilistic approach.