Kafil Hajlaoui

Optimizing text classification through efficient feature selection based on quality metric

Feature maximization is a cluster quality metric which favors clusters with maximum feature representation as regard to their associated data. In this paper we show that a simple adaptation of such metric can provide a highly efficient feature selection and feature contrasting model in the context of supervised classification. The method is experienced on different types of textual datasets. The paper illustrates that the proposed method provides a very significant performance increase, as compared to state of the art methods, in all the studied cases even when a single bag of words model is exploited for data description. Interestingly, the most significant performance gain is obtained in the case of the classification of highly unbalanced, highly multidimensional and noisy data, with a high degree of similarity between the classes.

Enhancing Patent Expertise through Automatic Matching with Scientific Papers

This paper focuses on a subtask of the QUAERO research program, a major innovating research project related to the automatic processing of multimedia and multilingual content. The objective discussed in this article is to propose a new method for the classification of scientific papers, developed in the context of an international patents classification plan related to the same field. The practical purpose of this work is to provide an assistance tool to experts in their task of evaluation of the originality and novelty of a patent, by offering to the latter the most relevant scientific citations. This issue raises new challenges in categorization research as the patent classification plan is not directly adapted to the structure of scientific documents, classes have high citation or cited topic and that there is not always a balanced distribution of the available examples within the different learning classes. We propose, as a solution to this problem, to apply an improved K-nearest-neighbors (KNN) algorithm based on the exploitation of association rules occurring between the index terms of the documents and the ones of the patent classes. By using a reference dataset of patents belonging to the field of pharmacology, on the one hand, and a bibliographic dataset of the same field issued from the Medline collection, on the other hand, we show that this new approach, which combines the advantages of numerical and symbolical approaches, improves considerably categorization performance, as compared to the usual categorization methods.

A New Feature Selection and Feature Contrasting Approach Based on Quality Metric: Application to Efficient Classification of Complex Textual Data

Feature maximization is a cluster quality metric which favors clusters with maximum feature representation as regard to their associated data. In this paper we go one step further showing that a straightforward adaptation of such metric can provide a highly efficient feature selection and feature contrasting model in the context of supervised classification. We more especially show that this technique can enhance the performance of classification methods whilst very significantly outperforming (+80%) the state-of-the art feature selection techniques in the case of the classification of unbalanced, highly multidimensional and noisy textual data, with a high degree of similarity between the classes.

Competence mining for collaborative virtual enterprise

In a context of decision-aid to support the identification of collaborative networks, this paper focuses on extracting essential facets of firm competencies. We present an approach for enrichment of competence ontology, based on two steps where a novel effective filtering step is utilized. First we extract the correlation between terms of a learning dataset using the generation of association rules. Second we retain the relevant new concepts using an extracted semantic information. The suggested approach was tested on an ontology of mechanical industry competencies. Experiments were performed on real data, which show the usefulness of our approach.

Enhanced semantic automatic ontology enrichment

With the fast growing development of the Web, the adoption of ontologies to improve the exploitation of information resources, is already heralded as a promising model of representation. However, the relevance of information that they contain requires regular updating, and specifically, the addition of new knowledge. Recently, new research approaches were defined in order to automatically enrich ontology. Usually they extensively use either statistical models or experts to provide the relevance and placement of new concepts. Unfortunately these approaches suffer the following drawback: The detection of new elements and position in ontology are not automatically established, and lack of use of semantic or syntactic information to extract relations between concepts. In this paper, we present an approach for ontology enrichment based on two steps where a novel effective filtering step is utilized. First we extract the correlation between terms of a learning dataset using the generation of association rules. Second we retain the relevant new concepts using an extracted semantic information. The suggested approach was tested on an ontology of mechanical industry competencies. Experiments were performed on real data, which show the usefulness of our approach.

Neural Network Based Text Mining to Discover Enterprise Networks

Abstract A web-oriented mechanism for information retrieval is presented. The motivation is to provide same decision support when forming collaborative production networks. In this case the subject is the mechanical industry. The focus is on information retrieval mechanisms. An interesting approach to automatically extract knowledge from information on activity field of a company, using its website as initial data is employed. Both a basic vector model and enhanced connectionist model with neural network are proposed. Their results are reported and compared.

A Novel Approach to Feature Selection Based on Quality Estimation Metrics

Feature maximization (F-max) is an unbiased quality estimation metric of unsupervised classification (clustering) that favours clusters with a maximal feature F-measure value. In this article we show that an adaptation of this metric within the framework of supervised classification allows efficient feature selection and feature contrasting to be performed. We experiment the method on different types of textual data. In this context, we demonstrate that this technique significantly improves the performance of classification methods as compared with the use of state-of-the art feature selection techniques, notably in the case of the classification of unbalanced, highly multidimensional and noisy textual data gathered in similar classes.

A promising combination of approaches for solving complex text classification tasks: application to the classification of scientific papers into patents classes

This paper focuses on a subtask of the QUAERO research program, a major innovating research project related to the automatic processing of multimedia and multilingual content. The objective discussed in this paper is to propose a new method for the classification of scientific papers, developed in the context of an international patents classification plan related to the same field. The practical purpose of this work is to provide an assistance tool to experts in their task of evaluation of the originality and novelty of a patent, by offering to the latter the most relevant scientific citations. This issue raises new challenges in categorisation research as the patent classification plan is not directly adapted to the structure of scientific documents, classes have high citation or cited topic and that there is not always a balanced distribution of the available examples within the different learning classes.

UNICOMP: Identification of Enterprise Competencies to Build Collaborative Networks

In a context of decision-aid to support the identification of collaborative networks, this paper focuses on extracting essential facets of firm competencies. Due to the complexity of the notion of competence, this contribution is based on a semantic representation of information using semantic ontology, bonds and a linguistic treatment based on the utilization of syntactic patterns. To identify enterprise competencies, the UNICOMP system uses company web sites as information source, as well as a general ontology of competencies as semantic resource.