%0 Journal Article
%T Selecting features with L1 regularization in Conditional Random Fields S¨¦lection de caract¨¦ristiques pour les champs al¨¦atoires conditionnels par p¨¦nalisation L1
%A Nataliya Sokolovska
%A Olivier Capp¨¦
%A Fran£¿ois Yvon
%J Traitement Automatique des Langues
%D 2010
%I Association pour le Traitement Automatique des Langues (ATALA)
%X Discriminative probabilistic models are able to cope with enriched linguistic representations, typically in the form of extremely large feature vectors. Working in high dimensional spaces is however problematic, and these problems are compounded in the case of structured output models, such as conditional random  elds (CRF). In this context, feature selection techniques help building more compact and ef cient models. In this work, we propose a novel estimation algorithm for CRF with L1 penalization, which yields sparse representations, thus implicitly selecting relevant features. We also report experiments conducted on two standard language engineering tasks (chunking and named Entity recognition), for which we analyze the generalization performance and the patterns of selected features. We  nally suggest various implementation speed-ups that should allow to ef ciently tackle even larger feature vectors.
%K conditional random  elds
%K probabilistic sequence models
%K feature selection
%U http://www.atala.org/IMG/pdf/TAL-2009-3-05-Yvon.pdf