@INPROCEEDINGS{grimal2011marami,
  author = {Cl{\'e}ment Grimal and Gilles Bisson},
  title = {Using a co-similarity approach on a large scale text categorization task},
  booktitle = {Seconde conf{\'e}rence sur les Mod{\`e}les et l′Analyse des R{\'e}seaux : 
Approches Math{\'e}ématiques et Informatique},
  year = {2011},
  abstract = {This paper presents a framework we developed for the second Large Scale Hierarchi-
cal Text Categorization challenge LSHTC2. The main idea is to propose a method allowing to
deal with the terms variability among the categories in order to be able to find similarities be-
tween collections of documents belonging to the same category but having few common terms.
Thus, we used a co-similarity based approach, named X-Sim, that we introduced in previous
work. Nevertheless, as this co-similarity methods are not highly scalable, we need to implement
a ``divide and conquer'' approach to split the categories into a set of clusters containing seman-
tically related documents. This lead to a two-stage strategy for the document categorization:
first, we decide in which cluster the test document belongs, and then inside the elected cluster,
we perform the final categorization that is based on our co-similarity approach.}
}