On statistical parsing of French with supervised and semi-supervised strategies

Marie Candito (1) , Benoît Crabbé (1) , Djamé Seddah (1, 2)

1 ALPAGE - Analyse Linguistique Profonde à Grande Echelle ; Large-scale deep linguistic processing
2 LaLIC - Langues, logiques, informatiques, cognition

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.

Mots clés: statistical parsing

Domaines: Informatique et langage [cs.CL]; Traitement du texte et du document; Intelligence artificielle [cs.AI]

Marie Candito, Benoît Crabbé, Djamé Seddah. On statistical parsing of French with supervised and semi-supervised strategies. EACL 2009 workshop on Computational Linguistic Aspects of Grammatical Inference, Mar 2009, Athens, Greece. pp.49-57. ⟨hal-00495290⟩