-
Sémantique textuelle et TAL : un exemple d'application à l'analyse des sentim...
Article à paraître en septembre 2014 dans DOCUMENTS, TEXTES, ŒUVRES. Perspectives sémiotiques (Driss ABLALI, Sémir BADIR, Dominique DUCARD, éd.), Presses Universitaires de Rennes. -
Temporal Logic in Natural Language Processing
In this paper, we clarify some linguistic concepts, studying the different levels of representation and processing of linguistic utterances. We also illustrated with... -
Recognition of Textual Inference a State of the Art
This paper is devoted to the study of textual inference, the presenta-tion of different applications of the Recognition of Textual Inference (RTE) and the main levels... -
Automatic pathology classification using a single feature machine learning - ...
International audience -
Identification of abnormal event by usage and flight data monitoring
International audience -
Online Parameter Tuning for Object Tracking Algorithms
International audience -
Reactive control and sensor fusion for mobile manipulators in human robot int...
In order to share a workspace with humans, a service robot should be able to safely interact within an unstructured environment. In this context, the robot shall adapt... -
Fault diagnosis using Support Vector Machines : application to different mult...
Real systems are usually nonlinear and their modeling and monitoring remains adifficult task. However, with advances in technology and the availability of big amounts... -
A comprehensive study of small non-frameshift insertions/deletions in protein...
International audience -
Sequential prediction for budgeted learning : Application to trigger design
Classification in machine learning has been extensively studied during the pastdecades. Many solutions have been proposed to output accurate classifiers and toobtain... -
Storing sparse messages in networks of neural cliques
International audience -
Handling imbalanced datasets by reconstruction rules in decomposition schemes
Disproportion among class priors is encountered in a large number of domains making conventional learning algorithms less effective in predicting samples belonging to... -
Graph-based semi-supervised learning methods and quick detection of central n...
Semi-supervised learning methods constitute a category of machine learning methods which use labelled points together with unlabeled data to tune the classifier. The...
