HAL : ujm-00109696, version 1

Fiche détaillée

Récupérer au format BibTeX - EndNote - TEI - RefWorks -

17th European Conference on Machine Learning, Berlin : Allemagne (2006)

Learning Stochastic Tree Edit Distance

Marc Bernard 1, Amaury Habrard 2, Marc Sebban 1

(09/2006)

Trees provide a suited structural representation to deal with complex tasks such as web information extraction, RNA secondary structure prediction, or conversion of tree structured documents. In this context, many applications require the calculation of similarities between tree pairs. The most studied distance is likely the tree edit distance for which improvements in terms of complexity have been achieved during the last decade. However, this classic edit distance usually uses a priori fixed edit costs which are often difficult to tune, that leaves little room for tackling complex problems. In this paper, we focus on the learning of a stochastic tree edit distance. We use an adaptation of the expectation-maximization algorithm for learning the primitive edit costs. We carried out several series of experiments that confirm the interest to learn a tree edit distance rather than a priori imposing edit costs.

1 :	LAboratoire Hubert Curien (LAHC)
	CNRS : UMR5516 – Université Jean Monnet - Saint-Etienne
2 :	Laboratoire d'informatique Fondamentale de Marseille (LIF)
	CNRS : UMR6166 – Université de la Méditerranée - Aix-Marseille II – Université de Provence - Aix-Marseille I

domaine

:

Informatique/Apprentissage

mots-clés : Stochastic tree edit distance – EM algorithm – generative models – discriminative models

ujm-00109696, version 1

http://hal-ujm.ccsd.cnrs.fr/ujm-00109696

oai:hal-ujm.ccsd.cnrs.fr:ujm-00109696

Contributeur : Marc Bernard <>

Soumis le : Jeudi 16 Novembre 2006, 11:47:54

Dernière modification le : Jeudi 23 Avril 2009, 14:16:11