On statistical parsing of French with supervised and semi-supervised strategies
Résumé
This paper reports preliminary results on grammatical induction for French. We investigate how to best train a parser on the French Treebank (Abeillé and Barrier, 2004), viewing the task as a trade-off between generalizability and interpretability. We compare on French a supervised lexicalized parsing algorithm with a semi-supervised unlexicalized algorithm Petrov et al. (2006) along the lines of Crabbé and Candito (2008). We report the best results known to us on French statistical parsing with the semi-supervised learning algorithm, and the reported experiments can give insights for the task of grammatical learning for a morphologically-rich language, with a relatively limited amount of training data, annotated with a rather flat structure.
Origine | Fichiers produits par l'(les) auteur(s) |
---|
Loading...