This website serves as a showcase for a project conducted for a course in our graduate program in Natural Language Processing (NLP). The course is operated between three universities (INALCO, Sorbonne Nouvelle and Paris Ouest) and is in continue of Projet Encadré I.


Projet Encadré, henceforth "PE", served as an opportunity to implement a collection of programs in order to obtain a semi-automatic textual processing. The process includes the very first steps of gathering data(online or already downloaded), normalizing according to our needed format and manipulating in order to facilitate further analyses. Each page on this site represents a stage in the project which required a specific set of tools and processes, hence the term "toolbox".

We would like to thank professors Serge Fleury, Jean-Michel Daube and Rachid Belmouhoub for their help and patience.

We invite you to take a deeper look at the aims of this project and to discover more about each phase »