Learning Multi-label Alternating Decision Trees from Texts and Data

Françesco de Comite (1) , Rémi Gilleron (1, 2) , Marc Tommasi (1, 2)

1 GRAppA - LIFL - Groupe de Recherche en Apprentissage Automatique
2 LIFL - Laboratoire d'Informatique Fondamentale de Lille

Multi-label decision procedures are the target of the supervised learning algorithm we propose in this paper. Multi-label decision procedures map examples to a finite set of labels. Our learning algorithm extends Schapire and Singer?s Adaboost.MH and produces sets of rules that can be viewed as trees like Alternating Decision Trees (invented by Freund and Mason). Experiments show that we take advantage of both performance and readability using boosting techniques as well as tree representations of large set of rules. Moreover, a key feature of our algorithm is the ability to handle heterogenous input data: discrete and continuous values and text data. Keywords boosting - alternating decision trees - text mining - multi-label problems

Domaines: Langage de programmation [cs.PL]

Françesco de Comite, Rémi Gilleron, Marc Tommasi. Learning Multi-label Alternating Decision Trees from Texts and Data. International Conference on Machine Learning and Data Mining, 2003, Leipzig, Georgia. pp.35-49. ⟨inria-00536733⟩